# Doitong API > One HTTP API for the best image, video and audio generation models. Same request shape for every model, upstream prices in USD (1000 API credits = 1 USD) with exact quotes before you run, output files kept forever (paid per GB-month) or 7 days for free (your choice), one error format, signed webhooks and an MCP server for AI agents. - API base URL: https://api.doitong.ru/v1 - Authentication: `Authorization: Bearer ` (keys at https://doitong.com/developers/dashboard#keys) - Run any model: `POST https://api.doitong.ru/v1/run/{model_id}?wait=20`; poll `GET https://api.doitong.ru/v1/requests/{id}` - Price for an input: `POST https://api.doitong.ru/v1/quote/{model_id}` (same body as run) — exact, except for models "charged by usage" (mode metered), where it is the most the run can cost and the unused part is refunded - MCP server (Streamable HTTP): `https://api.doitong.ru/v1/mcp` - Output files: kept forever by default (100 API credits per GB per month) or 7 days for free: account setting `PATCH https://api.doitong.ru/v1/account/storage`, per run `?storage=permanent|temporary`; delete with `DELETE https://api.doitong.ru/v1/requests/{id}/files` - Every page below also exists as Markdown: add `.md` to its URL. ## Guides - [Quickstart](https://doitong.com/developers/docs/quickstart.md): Get a key, run your first model and read the result in three steps. - [Authentication](https://doitong.com/developers/docs/authentication.md): API keys, scopes, per-key budgets and rate limits. - [Requests](https://doitong.com/developers/docs/requests.md): Find a model, run it, wait, poll, cancel, list and replay requests safely with idempotency keys. - [Webhooks](https://doitong.com/developers/docs/webhooks.md): Get a signed callback when a request finishes and verify it. - [Files](https://doitong.com/developers/docs/files.md): Pass images, video and audio as public URLs, data URIs or uploads. - [Errors](https://doitong.com/developers/docs/errors.md): One error format for every endpoint, with every type and code. - [Pricing](https://doitong.com/developers/docs/pricing.md): Upstream prices in USD, API credits, exact quotes before you run, and automatic refunds. - [Parameters](https://doitong.com/developers/docs/parameters.md): Canonical parameter names that work across models, and type coercion. - [MCP server](https://doitong.com/developers/docs/mcp.md): Use every model from Claude, Cursor and other MCP clients. - [Docs for AI agents](https://doitong.com/developers/docs/ai-agents.md): Hand these docs to Claude, ChatGPT or Cursor: llms.txt, Markdown twins, OpenAPI. ## Models: Text to Image (199) - Flux 2 (Black Forest Labs), from $0.005: - [FLUX 2 Flash](https://doitong.com/developers/models/flux-2/flash.md): `flux-2/flash`. $0.005 / megapixel. - [FLUX 2 Lora](https://doitong.com/developers/models/flux-2/lora.md): `flux-2/lora`. $0.021 / megapixel. - [FLUX 2 Turbo](https://doitong.com/developers/models/flux-2/turbo.md): `flux-2/turbo`. $0.008 / megapixel. - [FLUX.2 \[dev\]](https://doitong.com/developers/models/flux-2.md): `flux-2`. $0.012 / megapixel. - [FLUX.2 \[pro\]](https://doitong.com/developers/models/flux-2-pro.md): `flux-2-pro`. $0.015 / megapixel of output image. - FLUX.1 (Black Forest Labs), from $0.003: - [FLUX.1 \[dev\]](https://doitong.com/developers/models/flux/dev.md): `flux/dev`. $0.025 / megapixel. - [FLUX.1 \[schnell\]](https://doitong.com/developers/models/flux/schnell.md): `flux/schnell`. $0.003 / megapixel. - GPT Image 2.5 (OpenAI), from $0.008: - [GPT Image 2.5 Sunburst Text to Image](https://doitong.com/developers/models/openai/gpt-image-2.5/sunburst/text-to-image.md): `openai/gpt-image-2.5/sunburst/text-to-image`. $0.054 / image (estimated per run). - [GPT Image 2.5 Text to Image](https://doitong.com/developers/models/openai/gpt-image-2.5/flare/text-to-image.md): `openai/gpt-image-2.5/flare/text-to-image`. from $0.008 / image. - [Ideogram V4.5](https://doitong.com/developers/models/ideogram/v4.5.md): `ideogram/v4.5`. Ideogram's typography specialist for logos, posters and signage, in three quality levels. from $0.03 / image. - [Nano Banana 2](https://doitong.com/developers/models/nano-banana-2.md): `nano-banana-2`. Google's fast Gemini image model, from quick 0.5K drafts to 4K, with extreme aspect ratios and web grounding. from $0.06 / image. - [Nano Banana Pro](https://doitong.com/developers/models/nano-banana-pro.md): `nano-banana-pro`. Google's strongest image model, with reliable lettering, complex layouts and output up to 4K. from $0.15 / image. - Recraft v4 (Recraft), from $0.007: - [Recraft V4](https://doitong.com/developers/models/recraft/v4/text-to-image.md): `recraft/v4/text-to-image`. $0.04 / image. - [Recraft V4 (Vector)](https://doitong.com/developers/models/recraft/v4/text-to-vector.md): `recraft/v4/text-to-vector`. $0.08 / image. - [Recraft V4 Pro](https://doitong.com/developers/models/recraft/v4/pro/text-to-image.md): `recraft/v4/pro/text-to-image`. $0.25 / image. - [Recraft V4 Pro (Vector)](https://doitong.com/developers/models/recraft/v4/pro/text-to-vector.md): `recraft/v4/pro/text-to-vector`. $0.30 / image. - [Recraft V4.1 Flash Text to Image](https://doitong.com/developers/models/recraft/v4.1/flash/text-to-image.md): `recraft/v4.1/flash/text-to-image`. $0.007 / image. - [Recraft V4.1 Text to Image](https://doitong.com/developers/models/recraft/v4.1/text-to-image.md): `recraft/v4.1/text-to-image`. $0.035 / image. - [Recraft V4.1 Text to Image Pro](https://doitong.com/developers/models/recraft/v4.1/pro/text-to-image.md): `recraft/v4.1/pro/text-to-image`. $0.21 / image. - [Recraft V4.1 Text to Image Utility](https://doitong.com/developers/models/recraft/v4.1/utility/text-to-image.md): `recraft/v4.1/utility/text-to-image`. $0.035 / image. - [Recraft V4.1 Text to Vector](https://doitong.com/developers/models/recraft/v4.1/text-to-vector.md): `recraft/v4.1/text-to-vector`. $0.08 / image. - [Recraft V4.1 Text to Vector Pro](https://doitong.com/developers/models/recraft/v4.1/pro/text-to-vector.md): `recraft/v4.1/pro/text-to-vector`. $0.30 / image. - [Recraft V4.1 Utility Text to Image](https://doitong.com/developers/models/recraft/v4.1/utility/pro/text-to-image.md): `recraft/v4.1/utility/pro/text-to-image`. $0.21 / image. - [Seedream 5.0 Pro Text to Image](https://doitong.com/developers/models/bytedance/seedream/v5/pro/text-to-image.md): `bytedance/seedream/v5/pro/text-to-image`. ByteDance's flagship image model for editorial-grade photos and posters at up to 2K. from $0.0675 / run of output image. - [Wan v2.6 Text to Image](https://doitong.com/developers/models/wan/v2.6/text-to-image.md): `wan/v2.6/text-to-image`. Wan 2.6 text-to-image with an optional style reference image and up to 5 images per request. $0.03 / image. - [AuraFlow](https://doitong.com/developers/models/aura-flow.md): `aura-flow`. Open flow-based text-to-image model, generating one or two images per request with prompt expansion. $0.012 / image (estimated per run). - [Bagel](https://doitong.com/developers/models/bagel.md): `bagel`. Text-to-image generation with a multimodal 7B model and an optional thinking step. $0.10 / image. - [Bitdance](https://doitong.com/developers/models/bitdance.md): `bitdance`. Text-to-image generator built on an autoregressive language model, with up to four images per call. $0.01 / image (estimated per run). - [Boogu Image](https://doitong.com/developers/models/boogu-image.md): `boogu-image`. Bilingual English and Chinese text-to-image with negative prompts and adjustable guidance range. $0.04 / megapixel. - [Fibo](https://doitong.com/developers/models/bria/fibo/generate.md): `bria/fibo/generate`. Text-to-image model driven by plain or structured JSON prompts, with optional reference image and 1MP or 4MP output. $0.04 / image. - [CogView](https://doitong.com/developers/models/cogview4.md): `cogview4`. Text-to-image model from Zhipu AI that makes up to 4 images per call, in jpeg or png. $0.10 / megapixel. - [ControlNet SDXL](https://doitong.com/developers/models/fast-sdxl-controlnet-canny.md): `fast-sdxl-controlnet-canny`. SDXL text-to-image guided by a control image, for composition-locked generation. $0.015 / image (estimated per run). - [Cosmos 3 Super](https://doitong.com/developers/models/nvidia/cosmos-3-super/text-to-image.md): `nvidia/cosmos-3-super/text-to-image`. Text-to-image generation with prompt expansion and an optional agentic candidate-comparison mode. from $0.04 / run of output image. - [DeepSeek Janus-Pro](https://doitong.com/developers/models/janus.md): `janus`. Autoregressive text-to-image generator that returns up to 16 images per call, with temperature and CFG weight controls. $0.028 / image (estimated per run). - [Dreamshaper](https://doitong.com/developers/models/dreamshaper.md): `dreamshaper`. Stylized text-to-image diffusion model with LoRA and embedding support and up to 8 images per request. $0.02 / image (estimated per run). - Ernie Image (Baidu), from $0.01: - [Ernie Image](https://doitong.com/developers/models/ernie-image.md): `ernie-image`. $0.03 / image (estimated per run). - [Ernie Image Turbo](https://doitong.com/developers/models/ernie-image/turbo.md): `ernie-image/turbo`. $0.01 / image (estimated per run). - [Ernie Image Lora](https://doitong.com/developers/models/ernie-image/lora.md): `ernie-image/lora`. Ernie Image generation that merges up to 3 LoRAs for custom styles or subjects. $0.035 / image (estimated per run). - [Ernie Image Lora Turbo](https://doitong.com/developers/models/ernie-image/lora/turbo.md): `ernie-image/lora/turbo`. Turbo Ernie Image with LoRA support, tuned for 8 steps and up to 3 merged LoRAs. $0.015 / image (estimated per run). - [Fibo Bbq Preview](https://doitong.com/developers/models/bria/fibo-bbq-preview/generate.md): `bria/fibo-bbq-preview/generate`. Preview text-to-image model with structured prompt input and an adjustable guidance scale of 3 to 5. $0.04 / image. - [Fibo Gen 1.5 Text to Image](https://doitong.com/developers/models/bria/fibo-gen-1.5/text-to-image.md): `bria/fibo-gen-1.5/text-to-image`. Text-to-image model with plain or JSON-structured prompts and 1MP or 4MP output, without reference image. $0.04 / image. - [Fibo Lite](https://doitong.com/developers/models/bria/fibo-lite/generate.md): `bria/fibo-lite/generate`. Fast lightweight text-to-image model with structured prompt support and an optional reference image. $0.036 / image. - [Flux 2 Flex](https://doitong.com/developers/models/flux-2-flex.md): `flux-2-flex`. Text-to-image generator with adjustable steps and guidance, aimed at typography and text in images. $0.05 / megapixel of output image. - Flux 2 LoRA Gallery (Black Forest Labs), from $0.021: - [FLUX 2 Lora Gallery Hdr Style](https://doitong.com/developers/models/flux-2-lora-gallery/hdr-style.md): `flux-2-lora-gallery/hdr-style`. $0.021 / megapixel. - [FLUX 2 Lora Gallery Realism](https://doitong.com/developers/models/flux-2-lora-gallery/realism.md): `flux-2-lora-gallery/realism`. $0.021 / megapixel. - [Flux 2 Lora Gallery · Ballpoint Pen Sketch](https://doitong.com/developers/models/flux-2-lora-gallery/ballpoint-pen-sketch.md): `flux-2-lora-gallery/ballpoint-pen-sketch`. $0.021 / megapixel. - [Flux 2 Lora Gallery · Digital Comic Art](https://doitong.com/developers/models/flux-2-lora-gallery/digital-comic-art.md): `flux-2-lora-gallery/digital-comic-art`. $0.021 / megapixel. - [Flux 2 Lora Gallery · Satellite View Style](https://doitong.com/developers/models/flux-2-lora-gallery/satellite-view-style.md): `flux-2-lora-gallery/satellite-view-style`. $0.021 / megapixel. - [Flux 2 Lora Gallery · Sepia Vintage](https://doitong.com/developers/models/flux-2-lora-gallery/sepia-vintage.md): `flux-2-lora-gallery/sepia-vintage`. $0.021 / megapixel. - [Flux 2 Max](https://doitong.com/developers/models/flux-2-max.md): `flux-2-max`. Top-tier FLUX.2 text-to-image with adjustable safety tolerance and jpeg or png output. $0.03 / megapixel of output image. - Flux Krea LoRA (Black Forest Labs), from $0.035: - [Flux Krea Lora](https://doitong.com/developers/models/flux-krea-lora/stream.md): `flux-krea-lora/stream`. $0.035 / megapixel. - [FLUX.1 Krea \[dev\] with LoRAs](https://doitong.com/developers/models/flux-krea-lora.md): `flux-krea-lora`. $0.035 / megapixel. - Flux LoRA (Black Forest Labs), from $0.035: - [Flux Lora](https://doitong.com/developers/models/flux-lora/stream.md): `flux-lora/stream`. $0.035 / megapixel. - [FLUX.1 \[dev\] with LoRAs](https://doitong.com/developers/models/flux-lora.md): `flux-lora`. $0.035 / megapixel. - Flux Pro (Black Forest Labs), from $0.04: - [FLUX1.1 \[pro\]](https://doitong.com/developers/models/flux-pro/v1.1.md): `flux-pro/v1.1`. $0.04 / megapixel. - [FLUX1.1 \[pro\] ultra](https://doitong.com/developers/models/flux-pro/v1.1-ultra.md): `flux-pro/v1.1-ultra`. $0.06 / image. - [FLUX1.1 \[pro\] ultra Fine-tuned](https://doitong.com/developers/models/flux-pro/v1.1-ultra-finetuned.md): `flux-pro/v1.1-ultra-finetuned`. $0.07 / image. - FLUX.1 (Black Forest Labs), from $0.003: - [FLUX.1 · Flux 1 Schnell](https://doitong.com/developers/models/flux-1/schnell.md): `flux-1/schnell`. $0.003 / megapixel. - [FLUX.1 · Flux 1 · Dev](https://doitong.com/developers/models/flux-1/dev.md): `flux-1/dev`. $0.025 / megapixel. - [FLUX.1 \[dev\] Control LoRA Canny](https://doitong.com/developers/models/flux-control-lora-canny.md): `flux-control-lora-canny`. FLUX.1 dev text-to-image guided by a Canny edge control image. $0.04 / megapixel. - [FLUX.1 \[dev\] Control LoRA Depth](https://doitong.com/developers/models/flux-control-lora-depth.md): `flux-control-lora-depth`. FLUX.1 dev text-to-image guided by a depth map from a control image. $0.04 / megapixel. - [FLUX.1 \[dev\] with Controlnets and Loras](https://doitong.com/developers/models/flux-general.md): `flux-general`. FLUX.1 [dev] text-to-image with LoRAs, ControlNets, IP-Adapters, EasyControl and reference-image guidance. $0.30 / image (estimated per run). - [FLUX.1 Krea \[dev\]](https://doitong.com/developers/models/flux/krea.md): `flux/krea`. Text-to-image generator with 12B flow transformer, tunable steps, guidance, and up to four images per call. $0.025 / megapixel. - [FLUX.1 Krea · Flux 1](https://doitong.com/developers/models/flux-1/krea.md): `flux-1/krea`. FLUX.1 Krea [dev] text-to-image listed under the Flux 1 name, with steps and guidance controls. $0.025 / megapixel. - [FLUX.1 SRPO · Flux 1](https://doitong.com/developers/models/flux-1/srpo.md): `flux-1/srpo`. FLUX.1 SRPO text-to-image with preset sizes, up to 4 images and selectable acceleration. $0.025 / megapixel. - [FLUX.1 SRPO \[dev\]](https://doitong.com/developers/models/flux/srpo.md): `flux/srpo`. 12B-parameter FLUX.1 dev text-to-image variant with adjustable steps, guidance and an acceleration setting. $0.025 / megapixel. - [FLUX.1 Subject](https://doitong.com/developers/models/flux-subject.md): `flux-subject`. Fast FLUX.1 text-to-image that takes a subject reference image to keep a person, product or brand look. $0.04 / megapixel. - FLUX.2 (Black Forest Labs), from $0.01: - [FLUX.2 \[klein\] 4B Base LoRA](https://doitong.com/developers/models/flux-2/klein/4b/base/lora.md): `flux-2/klein/4b/base/lora`. $0.016 / megapixel. - [FLUX.2 \[klein\] 4B LoRA](https://doitong.com/developers/models/flux-2/klein/4b/lora.md): `flux-2/klein/4b/lora`. $0.01 / megapixel. - [FLUX.2 \[klein\] 9B Base LoRA](https://doitong.com/developers/models/flux-2/klein/9b/base/lora.md): `flux-2/klein/9b/base/lora`. $0.02 / megapixel. - [FLUX.2 \[klein\] 9B LoRA](https://doitong.com/developers/models/flux-2/klein/9b/lora.md): `flux-2/klein/9b/lora`. $0.015 / megapixel. - FLUX.2 (Black Forest Labs), from $0.005: - [FLUX.2 \[klein\] 4B](https://doitong.com/developers/models/flux-2/klein/4b.md): `flux-2/klein/4b`. $0.005 / megapixel. - [FLUX.2 \[klein\] 4B Base](https://doitong.com/developers/models/flux-2/klein/4b/base.md): `flux-2/klein/4b/base`. $0.009 / megapixel. - [FLUX.2 \[klein\] 9B](https://doitong.com/developers/models/flux-2/klein/9b.md): `flux-2/klein/9b`. $0.006 / megapixel. - [FLUX.2 \[klein\] 9B Base](https://doitong.com/developers/models/flux-2/klein/9b/base.md): `flux-2/klein/9b/base`. $0.011 / megapixel. - Fooocus (Open model), from $0.085: - [Fooocus](https://doitong.com/developers/models/fooocus.md): `fooocus`. $0.444 / image (estimated per run). - [Fooocus Image Prompt](https://doitong.com/developers/models/fooocus/image-prompt.md): `fooocus/image-prompt`. $0.085 / image (estimated per run). - [Fooocus · Fast Fooocus SDXL · Image to Image](https://doitong.com/developers/models/fast-fooocus-sdxl/image-to-image.md): `fast-fooocus-sdxl/image-to-image`. Fast SDXL Fooocus image-to-image that restyles a starting image from a prompt, up to 8 outputs. $0.012 / image (estimated per run). - [Gemini 2.5 Flash Image](https://doitong.com/developers/models/gemini-25-flash-image.md): `gemini-25-flash-image`. Google text-to-image model with ten aspect ratios, up to 4 images per call and png, jpeg or webp output. $0.0398 / image. - [Gemini 3 Pro Image Preview](https://doitong.com/developers/models/gemini-3-pro-image-preview.md): `gemini-3-pro-image-preview`. Gemini 3 Pro Image text-to-image at 1K, 2K or 4K, with optional web search and a system prompt. from $0.15 / image. - [Gemini 3.1 Flash Image Preview](https://doitong.com/developers/models/gemini-3.1-flash-image-preview.md): `gemini-3.1-flash-image-preview`. Gemini 3.1 Flash Image text-to-image with 0.5K to 4K output, extreme ratios, web search and thinking. from $0.06 / image. - [GLM Image](https://doitong.com/developers/models/glm-image.md): `glm-image`. Text-to-image model with prompt expansion, adjustable steps and guidance, and up to 4 images per call. $0.05 / image (estimated per run). - [GPT Image 1 Mini](https://doitong.com/developers/models/gpt-image-1-mini.md): `gpt-image-1-mini`. Smaller GPT Image text-to-image model with the same size, quality and background options. from $0.005 / run of output image. - [GPT Image 2 API](https://doitong.com/developers/models/openai/gpt-image-2.md): `openai/gpt-image-2`. GPT Image 2 text-to-image with flexible sizes up to 3840px edge, aimed at fine typography. $0.106 / image (estimated per run). - [GPT-Image 1.5](https://doitong.com/developers/models/gpt-image-1.5.md): `gpt-image-1.5`. Version 1.5 text-to-image defaulting to high quality, with prompts up to 32000 characters. from $0.009 / run of output image. - Grok Imagine Image (xAI), from $0.02: - [Grok Imagine Image](https://doitong.com/developers/models/xai/grok-imagine-image.md): `xai/grok-imagine-image`. $0.02 / image. - [Grok Imagine Image · Quality · Text to Image](https://doitong.com/developers/models/xai/grok-imagine-image/quality/text-to-image.md): `xai/grok-imagine-image/quality/text-to-image`. from $0.05 / image. - [Hidream I1 Dev](https://doitong.com/developers/models/hidream-i1-dev.md): `hidream-i1-dev`. HiDream-I1 Dev text-to-image, balanced preset with 28 default steps. $0.03 / megapixel. - [Hidream I1 Fast](https://doitong.com/developers/models/hidream-i1-fast.md): `hidream-i1-fast`. HiDream-I1 Fast text-to-image tuned for fewer steps, defaulting to 16. $0.01 / megapixel. - [Hidream I1 Full](https://doitong.com/developers/models/hidream-i1-full.md): `hidream-i1-full`. HiDream-I1 Full text-to-image with guidance scale and LoRA support, 50 default steps. $0.05 / megapixel. - Hidream O1 Image (HiDream), from $0.005: - [Hidream O1 Image](https://doitong.com/developers/models/hidream-o1-image.md): `hidream-o1-image`. $0.01 / megapixel. - [Hidream O1 Image · Dev](https://doitong.com/developers/models/hidream-o1-image/dev.md): `hidream-o1-image/dev`. $0.005 / megapixel. - [Hunyuan Image · v2.1 · Text to Image](https://doitong.com/developers/models/hunyuan-image/v2.1/text-to-image.md): `hunyuan-image/v2.1/text-to-image`. Hunyuan Image 2.1 text-to-image with negative prompt, optional refiner and reprompting. $0.10 / megapixel. - [Hunyuan Image · v3 · Text to Image](https://doitong.com/developers/models/hunyuan-image/v3/text-to-image.md): `hunyuan-image/v3/text-to-image`. Hunyuan Image 3.0 text-to-image with negative prompt and higher default guidance of 7.5. $0.10 / megapixel. - [Ideogram V2](https://doitong.com/developers/models/ideogram/v2.md): `ideogram/v2`. Text-to-image model with strong typography, 11 aspect ratios, style presets and a negative prompt. $0.08 / image. - [Ideogram V2 Turbo](https://doitong.com/developers/models/ideogram/v2/turbo.md): `ideogram/v2/turbo`. Faster Ideogram V2 text-to-image with typography strength, style presets and 11 aspect ratios. $0.05 / image. - Ideogram V2A (Ideogram), from $0.025: - [Ideogram V2A](https://doitong.com/developers/models/ideogram/v2a.md): `ideogram/v2a`. $0.04 / image. - [Ideogram V2A Turbo](https://doitong.com/developers/models/ideogram/v2a/turbo.md): `ideogram/v2a/turbo`. $0.025 / image. - Ideogram v3 (Ideogram), from $0.03: - [Ideogram Text to Image](https://doitong.com/developers/models/ideogram/v3.md): `ideogram/v3`. from $0.03 / image. - [Ideogram Transparent](https://doitong.com/developers/models/ideogram/v3/generate-transparent.md): `ideogram/v3/generate-transparent`. from $0.03 / image. - Ideogram v4 (Ideogram), from $0.006: - [Ideogram V4.0 Text to Image](https://doitong.com/developers/models/ideogram/v4.md): `ideogram/v4`. from $0.0075 / megapixel of output image. - [Ideogram V4.0q \[fast\]](https://doitong.com/developers/models/ideogram/v4/fast.md): `ideogram/v4/fast`. from $0.00525 / megapixel of output image. - [Ideogram V4.0q \[instant\]](https://doitong.com/developers/models/ideogram/v4/instant.md): `ideogram/v4/instant`. $0.0075 / megapixel of output image. - [Ideogram V4.0q Text to Image (LoRA)](https://doitong.com/developers/models/ideogram/v4/lora.md): `ideogram/v4/lora`. from $0.0113 / megapixel of output image. - [Illusion Diffusion](https://doitong.com/developers/models/illusion-diffusion.md): `illusion-diffusion`. Generates illusion-style images by conditioning a text prompt on an input image through ControlNet. $0.022 / run (estimated per run). - Juggernaut Flux (RunDiffusion), from $0.006: - [Juggernaut Flux Base](https://doitong.com/developers/models/rundiffusion/juggernaut-flux/base.md): `rundiffusion/juggernaut-flux/base`. $0.035 / megapixel. - [Juggernaut Flux Lightning](https://doitong.com/developers/models/rundiffusion/juggernaut-flux/lightning.md): `rundiffusion/juggernaut-flux/lightning`. $0.006 / megapixel. - [Juggernaut Flux Pro](https://doitong.com/developers/models/rundiffusion/juggernaut-flux/pro.md): `rundiffusion/juggernaut-flux/pro`. $0.055 / megapixel. - [Kling Image · O3 · Text to Image](https://doitong.com/developers/models/kling-image/o3/text-to-image.md): `kling-image/o3/text-to-image`. O3 text-to-image at 1K, 2K or 4K, with element-based face control and series output. from $0.028 / image. - [Kling Image · v3 · Text to Image](https://doitong.com/developers/models/kling-image/v3/text-to-image.md): `kling-image/v3/text-to-image`. v3 text-to-image with negative prompt and element face control at 1K or 2K. $0.028 / image. - [Kolors](https://doitong.com/developers/models/kolors.md): `kolors`. Text-to-image model aimed at photorealistic results, with scheduler choice and up to 8 images per request. $0.035 / image (estimated per run). - Krea 2 (Krea), from $0.015: - [Krea 2 Large](https://doitong.com/developers/models/krea/v2/large/text-to-image.md): `krea/v2/large/text-to-image`. from $0.06 / request. - [Krea 2 Medium](https://doitong.com/developers/models/krea/v2/medium/text-to-image.md): `krea/v2/medium/text-to-image`. from $0.03 / request. - [Krea 2 Medium Text to Image Turbo](https://doitong.com/developers/models/krea/v2/medium/turbo/text-to-image.md): `krea/v2/medium/turbo/text-to-image`. from $0.015 / request. - Krea 2 (Krea), from $0.008: - [Krea 2 Text to Image Turbo LoRA](https://doitong.com/developers/models/krea-2/turbo/lora.md): `krea-2/turbo/lora`. $0.01 / megapixel. - [Krea 2 Turbo](https://doitong.com/developers/models/krea-2/turbo.md): `krea-2/turbo`. $0.008 / megapixel. - [Krea 2 Text to Image Turbo Style](https://doitong.com/developers/models/krea-2/turbo/style.md): `krea-2/turbo/style`. Krea 2 Turbo text-to-image guided by one to three style reference images with an adjustable style scale. $0.01 / megapixel. - [Latent Consistency Models (v1.5/XL)](https://doitong.com/developers/models/fast-lcm-diffusion.md): `fast-lcm-diffusion`. Latent consistency text-to-image with few steps, up to 8 images per request. $0.005 / image (estimated per run). - [Longcat Image](https://doitong.com/developers/models/longcat-image.md): `longcat-image`. Text-to-image generator with six preset sizes, up to 4 images per call and png, jpeg or webp output. $0.13 / megapixel. - Luma Photon (Luma AI), from $0.005: - [Luma Photon](https://doitong.com/developers/models/luma-photon.md): `luma-photon`. $0.019 / run (estimated per run). - [Luma Photon Flash](https://doitong.com/developers/models/luma-photon/flash.md): `luma-photon/flash`. $0.005 / run (estimated per run). - Luma Uni-1 (Luma AI), from $0.042: - [Luma Uni-1 Text to Image](https://doitong.com/developers/models/luma/agent/uni-1/v1/text-to-image.md): `luma/agent/uni-1/v1/text-to-image`. $0.042 / image. - [Luma Uni-1 Text to Image Max](https://doitong.com/developers/models/luma/agent/uni-1/v1/max.md): `luma/agent/uni-1/v1/max`. $0.102 / image. - [Lumina Image 2](https://doitong.com/developers/models/lumina-image/v2.md): `lumina-image/v2`. Text-to-image model with typography focus, negative prompt, CFG controls and six size presets. $0.075 / megapixel. - [Mai Image 2.5 Text to Image](https://doitong.com/developers/models/microsoft/mai-image-2.5.md): `microsoft/mai-image-2.5`. Standard Microsoft MAI Image 2.5 text-to-image with typography and realism, up to 4 outputs. $0.05 / run of output image. - [MAI Image 2.5 Pro (Text to Image)](https://doitong.com/developers/models/microsoft/mai-image-2.5-pro.md): `microsoft/mai-image-2.5-pro`. Pro text-to-image model from Microsoft for typography-heavy, design-ready images in several formats. $0.332 / image (estimated per run). - [MiniMax (Hailuo AI) Text to Image](https://doitong.com/developers/models/minimax/image-01.md): `minimax/image-01`. MiniMax text-to-image with eight aspect ratios, up to nine images per request and optional prompt optimizer. $0.01 / image. - [MOSS Image](https://doitong.com/developers/models/moss-image.md): `moss-image`. Text-to-image model for Chinese and English text in images, with layout-aware prompts and optional expansion. $0.05 / megapixel. - [Nano Banana](https://doitong.com/developers/models/nano-banana.md): `nano-banana`. Original Nano Banana text-to-image generation with ten aspect ratios and up to four images. $0.0398 / image. - Nano Banana (Google), from $0.043: - [Nano Banana 2 Lite](https://doitong.com/developers/models/google/nano-banana-2-lite.md): `google/nano-banana-2-lite`. $0.043 / image (estimated per run). - [Nano Banana Lite](https://doitong.com/developers/models/google/nano-banana-lite.md): `google/nano-banana-lite`. $0.043 / image (estimated per run). - [Nano Banana 2.1](https://doitong.com/developers/models/google/nano-banana-2.1.md): `google/nano-banana-2.1`. Text-to-image with 1K/2K/4K output, extreme aspect ratios, web search and thinking levels. from $0.082 / image (estimated per run). - [Nucleus Image](https://doitong.com/developers/models/nucleus-image.md): `nucleus-image`. Text-to-image model with a sparse mixture-of-experts diffusion design and 7 aspect ratio presets. $0.01 / image (estimated per run). - [OmniGen v1](https://doitong.com/developers/models/omnigen-v1.md): `omnigen-v1`. Multimodal image generator for text prompts, editing, try-on and multi-person scenes with reference images. $0.20 / image (estimated per run). - [Omnigen V2](https://doitong.com/developers/models/omnigen-v2.md): `omnigen-v2`. Second-generation OmniGen with up to 3 input images, separate text and image guidance, and scheduler choice. $0.15 / megapixel. - [Ovis Image](https://doitong.com/developers/models/ovis-image.md): `ovis-image`. 7B-class text-to-image model aimed at fast, legible text rendering inside images. $0.012 / megapixel. - [Phota Text to Image](https://doitong.com/developers/models/phota.md): `phota`. Text-to-image with selectable base model and support for trained identity profiles in the prompt. from $0.09 / image. - [Playground v2.5](https://doitong.com/developers/models/playground-v25.md): `playground-v25`. Text-to-image generation with negative prompts, embeddings and up to 8 images per request. $0.013 / image (estimated per run). - [Pony V7](https://doitong.com/developers/models/pony-v7.md): `pony-v7`. Finetuned text-to-image model with noise source choice and up to 2 images per request. $0.03 / megapixel. - [Qwen Image](https://doitong.com/developers/models/qwen-image.md): `qwen-image`. Base text-to-image model with LoRA support, optional turbo mode and selectable acceleration. $0.02 / megapixel. - Qwen Image 2512 (Alibaba), from $0.02: - [Qwen Image 2512](https://doitong.com/developers/models/qwen-image-2512.md): `qwen-image-2512`. $0.02 / megapixel. - [Qwen Image 2512 · LoRA](https://doitong.com/developers/models/qwen-image-2512/lora.md): `qwen-image-2512/lora`. $0.035 / megapixel. - [Realistic Vision](https://doitong.com/developers/models/realistic-vision.md): `realistic-vision`. Photorealistic text-to-image diffusion model with LoRA and embedding support plus negative prompts. $0.009 / image (estimated per run). - [Recraft 20b](https://doitong.com/developers/models/recraft-20b.md): `recraft-20b`. Text-to-image model with many selectable styles, including vector and digital illustration, and color hints. from $0.022 / image. - RunDiffusion (RunDiffusion), from $0.045: - [Juggernaut Flux Base LoRA](https://doitong.com/developers/models/rundiffusion/juggernaut-flux-lora.md): `rundiffusion/juggernaut-flux-lora`. $0.045 / megapixel. - [Rundiffusion Photo Flux](https://doitong.com/developers/models/rundiffusion/rundiffusion-photo-flux.md): `rundiffusion/rundiffusion-photo-flux`. $0.045 / megapixel. - Sana (NVIDIA), from $0.008: - [Sana](https://doitong.com/developers/models/sana.md): `sana`. $0.001 / megapixel. - [Sana Sprint](https://doitong.com/developers/models/sana/sprint.md): `sana/sprint`. $0.0025 / megapixel. - [Sana v1.5 1.6B](https://doitong.com/developers/models/sana/v1.5/1.6b.md): `sana/v1.5/1.6b`. $0.0075 / megapixel. - [Sana v1.5 4.8B](https://doitong.com/developers/models/sana/v1.5/4.8b.md): `sana/v1.5/4.8b`. $0.01 / megapixel. - [SDXL ControlNet Union](https://doitong.com/developers/models/sdxl-controlnet-union.md): `sdxl-controlnet-union`. SDXL text-to-image guided by up to six control images: openpose, depth, teed, canny, normal, segmentation. $0.014 / image (estimated per run). - [Sensenova U1 Infographic](https://doitong.com/developers/models/sensenova-u1-infographic.md): `sensenova-u1-infographic`. Text-to-image tuned for infographics, with nine aspect ratios and optional reasoning before generation. from $0.05 / image. - [Stable Diffusion 3.5 Large](https://doitong.com/developers/models/stable-diffusion-v35-large.md): `stable-diffusion-v35-large`. Text-to-image diffusion transformer with negative prompts, LoRA, ControlNet and IP-Adapter support. $0.065 / image (estimated per run). - [Stable Diffusion 3.5 Medium](https://doitong.com/developers/models/stable-diffusion-v35-medium.md): `stable-diffusion-v35-medium`. Text-to-image diffusion transformer with negative prompts, adjustable steps and guidance, and up to 4 images per call. $0.02 / megapixel. - [Stable Diffusion v1.5](https://doitong.com/developers/models/stable-diffusion-v15.md): `stable-diffusion-v15`. Classic Stable Diffusion 1.5 text-to-image with LoRA and embedding support and up to 8 images per call. $0.004 / image (estimated per run). - [Stable Diffusion V3](https://doitong.com/developers/models/stable-diffusion-v3-medium.md): `stable-diffusion-v3-medium`. Stable Diffusion 3 Medium text-to-image with optional prompt expansion and up to 4 images. $0.035 / image. - [Stable Diffusion with LoRAs](https://doitong.com/developers/models/lora.md): `lora`. Text-to-image with any Stable Diffusion base model plus LoRAs, embeddings, ControlNets and IP adapters. $0.057 / image (estimated per run). - [Stable Diffusion XL](https://doitong.com/developers/models/fast-sdxl.md): `fast-sdxl`. SDXL text-to-image with LoRA and embedding support, negative prompts and up to 8 images per request. $0.005 / image (estimated per run). - [Stable Diffusion XL Lightning](https://doitong.com/developers/models/fast-lightning-sdxl.md): `fast-lightning-sdxl`. Few-step SDXL Lightning text-to-image limited to 1, 2, 4 or 8 inference steps. $0.004 / image (estimated per run). - [Vecglypher](https://doitong.com/developers/models/vecglypher.md): `vecglypher`. Generates vector glyphs as SVG paths from text plus a typographic style description. $0.005 / image. - [Vidu · Q2 · Text to Image](https://doitong.com/developers/models/vidu/q2/text-to-image.md): `vidu/q2/text-to-image`. Q2 text-to-image generator with 16:9, 9:16 and 1:1 outputs. $0.10 / image. - [Wan 2.5 Text to Image](https://doitong.com/developers/models/wan-25-preview/text-to-image.md): `wan-25-preview/text-to-image`. Wan 2.5 text-to-image with Chinese and English prompts and up to four images per call. $0.05 / image. - [Wan · v2.2 5b · Text to Image](https://doitong.com/developers/models/wan/v2.2-5b/text-to-image.md): `wan/v2.2-5b/text-to-image`. Compact 5B text-to-image model with six preset sizes, PNG or JPEG output and adjustable sampling steps. $0.016 / image. - [Wan · v2.2 A14b · Text to Image](https://doitong.com/developers/models/wan/v2.2-a14b/text-to-image.md): `wan/v2.2-a14b/text-to-image`. A14B text-to-image with two-stage guidance and six preset image sizes. $0.025 / image. - [Wan v2.2 A14B Text-to-Image A14B with LoRAs](https://doitong.com/developers/models/wan/v2.2-a14b/text-to-image/lora.md): `wan/v2.2-a14b/text-to-image/lora`. A14B text-to-image with LoRA weights for style adaptation, PNG or JPEG output. $0.05 / image. - Z Image Turbo (Alibaba), from $0.005: - [Z Image Base](https://doitong.com/developers/models/z-image/base.md): `z-image/base`. $0.01 / megapixel. - [Z Image Base Lora](https://doitong.com/developers/models/z-image/base/lora.md): `z-image/base/lora`. $0.012 / megapixel. - [Z Image Turbo](https://doitong.com/developers/models/z-image/turbo.md): `z-image/turbo`. $0.005 / megapixel. - [Z Image Turbo Lora](https://doitong.com/developers/models/z-image/turbo/lora.md): `z-image/turbo/lora`. $0.0085 / megapixel. - [Z-Image Turbo Seamless Tiling](https://doitong.com/developers/models/z-image/turbo/tiling.md): `z-image/turbo/tiling`. $0.02 / megapixel of output image. - [Z-Image Turbo Seamless Tiling Lora](https://doitong.com/developers/models/z-image/turbo/tiling/lora.md): `z-image/turbo/tiling/lora`. $0.025 / megapixel of output image. - [Qwen Image 3 Text to Image](https://doitong.com/developers/models/alibaba/qwen-image-3/text-to-image.md): `alibaba/qwen-image-3/text-to-image`. Alibaba's image model with excellent bilingual lettering, at 1K or 2K. from $0.04 / image. - Bria (Bria AI), from $0.112: - [Bria Text-to-Image Base](https://doitong.com/developers/models/bria/text-to-image/base.md): `bria/text-to-image/base`. $0.04 / image. - [Bria Text-to-Image Fast](https://doitong.com/developers/models/bria/text-to-image/fast.md): `bria/text-to-image/fast`. $0.028 / image. - [Bria Text-to-Image HD](https://doitong.com/developers/models/bria/text-to-image/hd.md): `bria/text-to-image/hd`. $0.04 / image. - [Bytedance Seedream V4 Text To Image](https://doitong.com/developers/models/bytedance/seedream/v4/text-to-image.md): `bytedance/seedream/v4/text-to-image`. Text-to-image generation with presets up to auto_4K, multi-image runs and selectable prompt enhancement. $0.03 / image. - [Bytedance Seedream V4.5 Text To Image](https://doitong.com/developers/models/bytedance/seedream/v4.5/text-to-image.md): `bytedance/seedream/v4.5/text-to-image`. Text-to-image generation at 2K to 4K sizes with optional multi-image output per request. $0.04 / image. - [Emu 3.5 Image · Text to Image](https://doitong.com/developers/models/emu-3.5-image/text-to-image.md): `emu-3.5-image/text-to-image`. Generates images from text alone, at 480p or 720p with a choice of nine aspect ratios. from $0.15 / image. - [Fibo 2.0 Generate](https://doitong.com/developers/models/bria/fibo-2/generate.md): `bria/fibo-2/generate`. Text-to-image model that expands prompts into structured VGL, with style presets and a reference image mode. $0.04 / image. - [Flux 3 Image · Text to Image](https://doitong.com/developers/models/blackforestlabs/flux-3/text-to-image.md): `blackforestlabs/flux-3/text-to-image`. Text-to-image with 512 to 4k resolution tiers, many aspect ratios and optional prompt expansion. from $0.048 / megapixel. - [Flux Kontext Lora · Text to Image](https://doitong.com/developers/models/flux-kontext-lora/text-to-image.md): `flux-kontext-lora/text-to-image`. Kontext [dev] text-to-image with merged LoRA support and optional acceleration levels. $0.035 / megapixel. - [FLUX.3 Klein](https://doitong.com/developers/models/blackforestlabs/flux-3/klein/text-to-image.md): `blackforestlabs/flux-3/klein/text-to-image`. Text-to-image with native 4K sizes, optional bounding-box layout control and up to 4 images per request. from $0.008 / run of output image. - [gpt-image-1 · Text to Image](https://doitong.com/developers/models/gpt-image-1/text-to-image.md): `gpt-image-1/text-to-image`. Original GPT Image text-to-image with selectable quality, background and three fixed sizes. from $0.011 / run of output image. - [Grok Imagine Image 2.0 · Text to Image](https://doitong.com/developers/models/xai/grok-imagine-image/v2.0/text-to-image.md): `xai/grok-imagine-image/v2.0/text-to-image`. Grok Imagine 2.0 text-to-image with 13 aspect ratios, 1k or 2k resolution, and up to 4 images. from $0.04 / run of output image. - [Hunyuan Image 3.0 Instruct](https://doitong.com/developers/models/hunyuan-image/v3/instruct/text-to-image.md): `hunyuan-image/v3/instruct/text-to-image`. Instruct version of Hunyuan Image 3.0 for text-to-image, with internal prompt expansion on by default. $0.36 / image (estimated per run). - [Krea 3 Text to Image](https://doitong.com/developers/models/krea/v3/text-to-image.md): `krea/v3/text-to-image`. Krea 3 text-to-image with berry or jam variants, prompt expansion and sizes up to about 4.2 megapixels. $0.025 / run (estimated per run). - [Meta Muse Image Text to Image](https://doitong.com/developers/models/meta/muse-image/text-to-image.md): `meta/muse-image/text-to-image`. Text-to-image generator with free-form aspect ratios and 1 to 10 images per request. $0.01 / image. - [PATINA · Material](https://doitong.com/developers/models/patina/material.md): `patina/material`. Text-to-texture generator that outputs tileable images plus PBR maps, with optional img2img and inpainting. from $0.08 / run. - [Qwen Image Max · Text to Image](https://doitong.com/developers/models/qwen-image-max/text-to-image.md): `qwen-image-max/text-to-image`. Text-to-image generation with Qwen Image Max, aimed at realistic, natural-looking results. $0.075 / image. - [Recraft V3 · Text to Image](https://doitong.com/developers/models/recraft/v3/text-to-image.md): `recraft/v3/text-to-image`. Text-to-image with a large style list, vector and illustration modes, and optional color palette control. from $0.04 / image. - [Seedream · Flash · Text to Image](https://doitong.com/developers/models/bytedance/seedream/v5/flash/text-to-image.md): `bytedance/seedream/v5/flash/text-to-image`. Seedream 5 Flash text-to-image with 1 to 6 outputs per request and jpeg or png output. $0.027 / image. - [Seedream · Lite · Text to Image](https://doitong.com/developers/models/bytedance/seedream/v5/lite/text-to-image.md): `bytedance/seedream/v5/lite/text-to-image`. Seedream 5 Lite text-to-image with 2K to 4K size tiers and multi-image generation. $0.035 / image. - Wan 27 (Alibaba), from $0.03: - [Wan · v2.7 · Pro · Text to Image](https://doitong.com/developers/models/wan/v2.7/pro/text-to-image.md): `wan/v2.7/pro/text-to-image`. $0.075 / image. - [Wan · v2.7 · Text to Image](https://doitong.com/developers/models/wan/v2.7/text-to-image.md): `wan/v2.7/text-to-image`. $0.03 / image. - [Ideogram · Custom Models · Generate](https://doitong.com/developers/models/ideogram/custom-models/generate.md): `ideogram/custom-models/generate`. Generates images from a trained custom Ideogram model identified by model_id. from $0.03 / image. - Recraft V4 Styles (Recraft), from $0.035: - [Recraft V4 Styles Pro Text to Image](https://doitong.com/developers/models/recraft/v4/style/pro/text-to-image.md): `recraft/v4/style/pro/text-to-image`. from $0.10 / image. - [Recraft V4 Styles Pro Text to Vector](https://doitong.com/developers/models/recraft/v4/style/pro/text-to-vector.md): `recraft/v4/style/pro/text-to-vector`. from $0.12 / image. - [Recraft V4 Styles Text to Image](https://doitong.com/developers/models/recraft/v4/style/text-to-image.md): `recraft/v4/style/text-to-image`. from $0.035 / image. - [Recraft V4 Styles Text to Vector](https://doitong.com/developers/models/recraft/v4/style/text-to-vector.md): `recraft/v4/style/text-to-vector`. from $0.05 / image. ## Models: Image Editing (376) - Flux 2 (Black Forest Labs), from $0.005: - [FLUX 2 Edit](https://doitong.com/developers/models/flux-2/edit.md): `flux-2/edit`. $0.012 / megapixel. - [FLUX 2 Flash Edit](https://doitong.com/developers/models/flux-2/flash/edit.md): `flux-2/flash/edit`. $0.005 / megapixel. - [FLUX 2 Lora Edit](https://doitong.com/developers/models/flux-2/lora/edit.md): `flux-2/lora/edit`. $0.021 / megapixel. - [FLUX 2 Pro Edit](https://doitong.com/developers/models/flux-2-pro/edit.md): `flux-2-pro/edit`. $0.105 / run (estimated per run). - [FLUX 2 Pro Outpaint](https://doitong.com/developers/models/flux-2-pro/outpaint.md): `flux-2-pro/outpaint`. $0.40 / run (estimated per run). - [FLUX 2 Turbo Edit](https://doitong.com/developers/models/flux-2/turbo/edit.md): `flux-2/turbo/edit`. $0.008 / megapixel. - FLUX.1 (Black Forest Labs), from $0.025: - [FLUX.1 \[dev\] Redux](https://doitong.com/developers/models/flux/dev/redux.md): `flux/dev/redux`. $0.025 / megapixel. - [FLUX.1 \[schnell\] Redux](https://doitong.com/developers/models/flux/schnell/redux.md): `flux/schnell/redux`. $0.025 / megapixel. - [FLUX.1 · Dev · Image to Image](https://doitong.com/developers/models/flux/dev/image-to-image.md): `flux/dev/image-to-image`. $0.09 / image (estimated per run). - GPT Image 2.5 (OpenAI), from $0.12: - [GPT Image 2.5 Edit](https://doitong.com/developers/models/openai/gpt-image-2.5/flare/edit.md): `openai/gpt-image-2.5/flare/edit`. from $0.12 / image (estimated per run). - [GPT Image 2.5 Sunburst Edit](https://doitong.com/developers/models/openai/gpt-image-2.5/sunburst/edit.md): `openai/gpt-image-2.5/sunburst/edit`. $0.128 / image (estimated per run). - [Ideogram V4.5 Edit](https://doitong.com/developers/models/ideogram/v4.5/edit.md): `ideogram/v4.5/edit`. Ideogram 4.5 prompt-based image edit with optional mask, up to 4 references and a high-precision mode. from $0.008 / image. - [Nano Banana 2 Edit](https://doitong.com/developers/models/nano-banana-2/edit.md): `nano-banana-2/edit`. Fast instruction-based editing that can also read a video, audio clip or PDF as context. from $0.06 / image. - [Nano Banana Pro Edit](https://doitong.com/developers/models/nano-banana-pro/edit.md): `nano-banana-pro/edit`. Edit or combine photos with plain-language instructions, keeping faces and products intact, up to 4K. from $0.15 / image. - [Seedream 5.0 Pro Edit](https://doitong.com/developers/models/bytedance/seedream/v5/pro/edit.md): `bytedance/seedream/v5/pro/edit`. Multi-image editing with Seedream 5.0 Pro, combining up to ten references into one 2K picture. from $0.0675 / run of output image. - [Wan v2.6 Image to Image](https://doitong.com/developers/models/wan/v2.6/image-to-image.md): `wan/v2.6/image-to-image`. Edits or restyles using 1-3 reference images and a prompt, with up to 4 outputs per request. $0.03 / image. - [Bagel · Edit](https://doitong.com/developers/models/bagel/edit.md): `bagel/edit`. Edits an existing image from a text instruction using the multimodal Bagel model. $0.10 / image. - [Boogu Image · Edit](https://doitong.com/developers/models/boogu-image/edit.md): `boogu-image/edit`. Instruction-based image editing from an input image, with separate text and image guidance strengths. $0.08 / image (estimated per run). - ControlNet SDXL (Stability AI), from $0.014: - [ControlNet SDXL · Image to Image](https://doitong.com/developers/models/fast-sdxl-controlnet-canny/image-to-image.md): `fast-sdxl-controlnet-canny/image-to-image`. $0.015 / image (estimated per run). - [ControlNet SDXL · Inpainting](https://doitong.com/developers/models/fast-sdxl-controlnet-canny/inpainting.md): `fast-sdxl-controlnet-canny/inpainting`. $0.014 / image (estimated per run). - [Flux 2 Flex · Edit](https://doitong.com/developers/models/flux-2-flex/edit.md): `flux-2-flex/edit`. Edit variant of Flex that changes images from a prompt, using one or more reference images. $0.334 / run (estimated per run). - Flux 2 LoRA Gallery (Black Forest Labs), from $0.021: - [Flux 2 Lora Gallery · Add Background](https://doitong.com/developers/models/flux-2-lora-gallery/add-background.md): `flux-2-lora-gallery/add-background`. $0.021 / image (estimated per run). - [Flux 2 Lora Gallery · Apartment Staging](https://doitong.com/developers/models/flux-2-lora-gallery/apartment-staging.md): `flux-2-lora-gallery/apartment-staging`. $0.021 / image (estimated per run). - [Flux 2 Lora Gallery · Face to Full Portrait](https://doitong.com/developers/models/flux-2-lora-gallery/face-to-full-portrait.md): `flux-2-lora-gallery/face-to-full-portrait`. $0.021 / image (estimated per run). - [Flux 2 Lora Gallery · Multiple Angles](https://doitong.com/developers/models/flux-2-lora-gallery/multiple-angles.md): `flux-2-lora-gallery/multiple-angles`. $0.021 / image (estimated per run). - [Flux 2 Lora Gallery · Virtual Tryon](https://doitong.com/developers/models/flux-2-lora-gallery/virtual-tryon.md): `flux-2-lora-gallery/virtual-tryon`. $0.021 / image (estimated per run). - [Flux 2 Max · Edit](https://doitong.com/developers/models/flux-2-max/edit.md): `flux-2-max/edit`. Top-tier FLUX.2 editing from a prompt and a list of input images, with an auto size option. $0.22 / run (estimated per run). - Flux Krea LoRA (Black Forest Labs), from $0.035: - [FLUX.1 Krea \[dev\] Inpainting with LoRAs](https://doitong.com/developers/models/flux-krea-lora/inpainting.md): `flux-krea-lora/inpainting`. $0.035 / image (estimated per run). - [FLUX.1 Krea \[dev\] with LoRAs · Image to Image](https://doitong.com/developers/models/flux-krea-lora/image-to-image.md): `flux-krea-lora/image-to-image`. $0.07 / image (estimated per run). - Flux LoRA (Black Forest Labs), from $0.035: - [FLUX.1 \[dev\] Inpainting with LoRAs](https://doitong.com/developers/models/flux-lora/inpainting.md): `flux-lora/inpainting`. $0.07 / image (estimated per run). - [FLUX.1 \[dev\] with LoRAs · Image to Image](https://doitong.com/developers/models/flux-lora/image-to-image.md): `flux-lora/image-to-image`. $0.035 / image (estimated per run). - Flux Pro (Black Forest Labs), from $0.05: - [FLUX.1 \[pro\] Fill](https://doitong.com/developers/models/flux-pro/v1/fill.md): `flux-pro/v1/fill`. $0.05 / image (estimated per run). - [FLUX.1 \[pro\] Fill Fine-tuned](https://doitong.com/developers/models/flux-pro/v1/fill-finetuned.md): `flux-pro/v1/fill-finetuned`. $0.06 / image (estimated per run). - [FLUX1.1 \[pro\] Redux](https://doitong.com/developers/models/flux-pro/v1.1/redux.md): `flux-pro/v1.1/redux`. $0.05 / megapixel. - [FLUX1.1 \[pro\] ultra Redux](https://doitong.com/developers/models/flux-pro/v1.1-ultra/redux.md): `flux-pro/v1.1-ultra/redux`. $0.05 / image (estimated per run). - FLUX.1 (Black Forest Labs), from $0.003: - [FLUX.1 \[dev\] Redux · Flux 1](https://doitong.com/developers/models/flux-1/dev/redux.md): `flux-1/dev/redux`. $0.025 / megapixel. - [FLUX.1 \[schnell\] Redux · Flux 1](https://doitong.com/developers/models/flux-1/schnell/redux.md): `flux-1/schnell/redux`. $0.003 / megapixel. - [FLUX.1 · Flux 1 · Dev · Image to Image](https://doitong.com/developers/models/flux-1/dev/image-to-image.md): `flux-1/dev/image-to-image`. $0.09 / image (estimated per run). - [FLUX.1 \[dev\] Control LoRA Canny · Image to Image](https://doitong.com/developers/models/flux-control-lora-canny/image-to-image.md): `flux-control-lora-canny/image-to-image`. Canny-edge control LoRA that restyles a starting image, with strength. $0.08 / image (estimated per run). - [FLUX.1 \[dev\] Control LoRA Depth · Image to Image](https://doitong.com/developers/models/flux-control-lora-depth/image-to-image.md): `flux-control-lora-depth/image-to-image`. Depth-map control LoRA that remakes an initial image with new structure. $0.08 / image (estimated per run). - FLUX.1 \[dev\] with Controlnets and Loras (Black Forest Labs), from $0.025: - [FLUX.1 \[dev\] with Controlnets and Loras · Differential Diffusion](https://doitong.com/developers/models/flux-general/differential-diffusion.md): `flux-general/differential-diffusion`. $0.138 / image (estimated per run). - [FLUX.1 \[dev\] with Controlnets and Loras · Image to Image](https://doitong.com/developers/models/flux-general/image-to-image.md): `flux-general/image-to-image`. $0.15 / image (estimated per run). - [FLUX.1 \[dev\] with Controlnets and Loras · Inpainting](https://doitong.com/developers/models/flux-general/inpainting.md): `flux-general/inpainting`. $0.192 / image (estimated per run). - [FLUX.1 \[dev\] with Controlnets and Loras · Rf Inversion](https://doitong.com/developers/models/flux-general/rf-inversion.md): `flux-general/rf-inversion`. $0.025 / image (estimated per run). - FLUX.1 Krea (Black Forest Labs), from $0.025: - [FLUX.1 Krea \[dev\] Redux](https://doitong.com/developers/models/flux/krea/redux.md): `flux/krea/redux`. $0.025 / megapixel. - [FLUX.1 Krea · Image to Image](https://doitong.com/developers/models/flux/krea/image-to-image.md): `flux/krea/image-to-image`. $0.075 / image (estimated per run). - FLUX.1 Krea (Black Forest Labs), from $0.025: - [FLUX.1 Krea \[dev\] Redux · Flux 1](https://doitong.com/developers/models/flux-1/krea/redux.md): `flux-1/krea/redux`. $0.025 / megapixel. - [FLUX.1 Krea · Flux 1 · Image to Image](https://doitong.com/developers/models/flux-1/krea/image-to-image.md): `flux-1/krea/image-to-image`. $0.075 / image (estimated per run). - [FLUX.1 SRPO · Flux 1 · Image to Image](https://doitong.com/developers/models/flux-1/srpo/image-to-image.md): `flux-1/srpo/image-to-image`. FLUX.1 SRPO image-to-image that restyles a source image from a prompt, with adjustable strength. $0.075 / image (estimated per run). - [FLUX.1 SRPO · Image to Image](https://doitong.com/developers/models/flux/srpo/image-to-image.md): `flux/srpo/image-to-image`. FLUX.1 SRPO [dev] image-to-image that reworks an input image under a text prompt. $0.075 / image (estimated per run). - FLUX.2 (Black Forest Labs), from $0.01: - [FLUX.2 \[klein\] 4B Base LoRA · Edit](https://doitong.com/developers/models/flux-2/klein/4b/base/edit/lora.md): `flux-2/klein/4b/base/edit/lora`. $0.016 / megapixel. - [FLUX.2 \[klein\] 4B LoRA · Edit](https://doitong.com/developers/models/flux-2/klein/4b/edit/lora.md): `flux-2/klein/4b/edit/lora`. $0.01 / megapixel. - [FLUX.2 \[klein\] 9B Base LoRA · Edit](https://doitong.com/developers/models/flux-2/klein/9b/base/edit/lora.md): `flux-2/klein/9b/base/edit/lora`. $0.02 / megapixel. - [FLUX.2 \[klein\] 9B LoRA · Edit](https://doitong.com/developers/models/flux-2/klein/9b/edit/lora.md): `flux-2/klein/9b/edit/lora`. $0.015 / megapixel. - FLUX.2 (Black Forest Labs), from $0.009: - [FLUX.2 \[klein\] 4B Base · Edit](https://doitong.com/developers/models/flux-2/klein/4b/base/edit.md): `flux-2/klein/4b/base/edit`. $0.009 / megapixel. - [FLUX.2 \[klein\] 4B · Edit](https://doitong.com/developers/models/flux-2/klein/4b/edit.md): `flux-2/klein/4b/edit`. $0.01 / image (estimated per run). - [FLUX.2 \[klein\] 9B Base · Edit](https://doitong.com/developers/models/flux-2/klein/9b/base/edit.md): `flux-2/klein/9b/base/edit`. $0.011 / megapixel. - [FLUX.2 \[klein\] 9B · Edit](https://doitong.com/developers/models/flux-2/klein/9b/edit.md): `flux-2/klein/9b/edit`. $0.011 / megapixel. - [Fooocus Inpainting](https://doitong.com/developers/models/fooocus/inpaint.md): `fooocus/inpaint`. Inpaints or outpaints an image with an optional mask, with modes for detail fixes or content changes. $0.055 / image (estimated per run). - [Gemini 2.5 Flash Image · Edit](https://doitong.com/developers/models/gemini-25-flash-image/edit.md): `gemini-25-flash-image/edit`. Gemini 2.5 Flash Image editing that works on one or more input images guided by a text prompt. $0.0398 / image. - [Gemini 3 Pro Image Preview · Edit](https://doitong.com/developers/models/gemini-3-pro-image-preview/edit.md): `gemini-3-pro-image-preview/edit`. Gemini 3 Pro Image editing from reference images, with 1K to 4K output and web search option. from $0.15 / image. - [Gemini 3.1 Flash Image Preview · Edit](https://doitong.com/developers/models/gemini-3.1-flash-image-preview/edit.md): `gemini-3.1-flash-image-preview/edit`. Gemini 3.1 Flash Image editing that also accepts video, audio or PDF context alongside images. from $0.06 / image. - [Glm Image · Image to Image](https://doitong.com/developers/models/glm-image/image-to-image.md): `glm-image/image-to-image`. Image-conditioned GLM variant for editing, style transfer and consistent characters from up to 4 references. $0.05 / image (estimated per run). - [GPT Image 1 Mini · Edit](https://doitong.com/developers/models/gpt-image-1-mini/edit.md): `gpt-image-1-mini/edit`. Smaller GPT Image model for editing from reference images, without a mask or fidelity option. from $0.005 / run of output image. - [GPT Image 2 API · Edit](https://doitong.com/developers/models/openai/gpt-image-2/edit.md): `openai/gpt-image-2/edit`. GPT Image 2 editing with up to 16 reference images and optional mask. $0.222 / image (estimated per run). - [GPT-Image 1.5 · Edit](https://doitong.com/developers/models/gpt-image-1.5/edit.md): `gpt-image-1.5/edit`. Version 1.5 image editing with optional mask for targeted changes and a high input fidelity default. from $0.009 / run of output image. - Grok Imagine Image (xAI), from $0.022: - [Grok Imagine Image Editing Quality](https://doitong.com/developers/models/xai/grok-imagine-image/quality/edit.md): `xai/grok-imagine-image/quality/edit`. from $0.05 / run of output image. - [Grok Imagine Image · Edit](https://doitong.com/developers/models/xai/grok-imagine-image/edit.md): `xai/grok-imagine-image/edit`. $0.022 / image. - [Hidream I1 Full · Image to Image](https://doitong.com/developers/models/hidream-i1-full/image-to-image.md): `hidream-i1-full/image-to-image`. HiDream-I1 Full image-to-image edit driven by a prompt, with adjustable denoising strength. $0.10 / image (estimated per run). - [Hidream O1 Image · Edit](https://doitong.com/developers/models/hidream-o1-image/edit.md): `hidream-o1-image/edit`. Full-quality reference-image editing and subject personalization, up to about 2048x2048, 50 steps. $0.01 / megapixel. - Ideogram V2 (Ideogram), from $0.08: - [Ideogram V2 Edit](https://doitong.com/developers/models/ideogram/v2/edit.md): `ideogram/v2/edit`. $0.08 / image. - [Ideogram V2 Remix](https://doitong.com/developers/models/ideogram/v2/remix.md): `ideogram/v2/remix`. $0.08 / image. - Ideogram V2 Turbo (Ideogram), from $0.05: - [Ideogram V2 Turbo Edit](https://doitong.com/developers/models/ideogram/v2/turbo/edit.md): `ideogram/v2/turbo/edit`. $0.05 / image. - [Ideogram V2 Turbo Remix](https://doitong.com/developers/models/ideogram/v2/turbo/remix.md): `ideogram/v2/turbo/remix`. $0.05 / image. - Ideogram V2A (Ideogram), from $0.025: - [Ideogram V2A Remix](https://doitong.com/developers/models/ideogram/v2a/remix.md): `ideogram/v2a/remix`. $0.04 / image. - [Ideogram V2A Turbo Remix](https://doitong.com/developers/models/ideogram/v2a/turbo/remix.md): `ideogram/v2a/turbo/remix`. $0.025 / image. - Ideogram v3 (Ideogram), from $0.03: - [Ideogram Object Removal](https://doitong.com/developers/models/ideogram/object-removal.md): `ideogram/object-removal`. $0.03 / image. - [Ideogram Replace Background](https://doitong.com/developers/models/ideogram/v3/replace-background.md): `ideogram/v3/replace-background`. from $0.03 / image. - [Ideogram V3 Edit](https://doitong.com/developers/models/ideogram/v3/edit.md): `ideogram/v3/edit`. from $0.03 / image. - [Ideogram · v3 · Layerize Text](https://doitong.com/developers/models/ideogram/v3/layerize-text.md): `ideogram/v3/layerize-text`. $0.09 / image. - [Ideogram · v3 · Reframe](https://doitong.com/developers/models/ideogram/v3/reframe.md): `ideogram/v3/reframe`. from $0.03 / image. - [Ideogram · v3 · Remix](https://doitong.com/developers/models/ideogram/v3/remix.md): `ideogram/v3/remix`. from $0.03 / image. - Ideogram v4 (Ideogram), from $0.008: - [Ideogram V4.0q Image to Image](https://doitong.com/developers/models/ideogram/v4/image-to-image.md): `ideogram/v4/image-to-image`. from $0.0075 / megapixel of output image. - [Ideogram V4.0q Image to Image LoRA](https://doitong.com/developers/models/ideogram/v4/image-to-image/lora.md): `ideogram/v4/image-to-image/lora`. from $0.0113 / megapixel of output image. - [Ideogram V4.0q Tiling](https://doitong.com/developers/models/ideogram/v4/tiling.md): `ideogram/v4/tiling`. from $0.03 / megapixel. - [Ideogram V4.0q Tiling LoRA](https://doitong.com/developers/models/ideogram/v4/tiling/lora.md): `ideogram/v4/tiling/lora`. from $0.0338 / megapixel. - Juggernaut Flux (RunDiffusion), from $0.035: - [Juggernaut Flux Base · Image to Image](https://doitong.com/developers/models/rundiffusion/juggernaut-flux/base/image-to-image.md): `rundiffusion/juggernaut-flux/base/image-to-image`. $0.035 / image (estimated per run). - [Juggernaut Flux Pro · Image to Image](https://doitong.com/developers/models/rundiffusion/juggernaut-flux/pro/image-to-image.md): `rundiffusion/juggernaut-flux/pro/image-to-image`. $0.055 / image (estimated per run). - [Kling Image · O3 · Image to Image](https://doitong.com/developers/models/kling-image/o3/image-to-image.md): `kling-image/o3/image-to-image`. O3 image editing from up to 10 reference images, with 1K-4K output and series mode. from $0.028 / image. - [Kling Image · v3 · Image to Image](https://doitong.com/developers/models/kling-image/v3/image-to-image.md): `kling-image/v3/image-to-image`. v3 image-to-image restyling from a single reference image, at 1K or 2K, up to 9 outputs. $0.028 / image. - [Kolors Image to Image](https://doitong.com/developers/models/kolors/image-to-image.md): `kolors/image-to-image`. Kolors image-to-image variant that restyles an input image from a prompt, with a strength control. $0.009 / image (estimated per run). - Latent Consistency Models (Open model), from $0.014: - [Latent Consistency Models (v1.5/XL) · Image to Image](https://doitong.com/developers/models/fast-lcm-diffusion/image-to-image.md): `fast-lcm-diffusion/image-to-image`. $0.019 / image (estimated per run). - [Latent Consistency Models (v1.5/XL) · Inpainting](https://doitong.com/developers/models/fast-lcm-diffusion/inpainting.md): `fast-lcm-diffusion/inpainting`. $0.014 / image (estimated per run). - [Longcat Image · Edit](https://doitong.com/developers/models/longcat-image/edit.md): `longcat-image/edit`. Prompt-based editing of an existing image, returning up to 4 variants. $0.30 / image (estimated per run). - Luma Photon (Luma AI), from $0.005: - [Luma Photon Flash Reframe](https://doitong.com/developers/models/luma-photon/flash/reframe.md): `luma-photon/flash/reframe`. $0.005 / run (estimated per run). - [Luma Photon Reframe](https://doitong.com/developers/models/luma-photon/reframe.md): `luma-photon/reframe`. $0.019 / run (estimated per run). - [Luma Photon · Flash · Modify](https://doitong.com/developers/models/luma-photon/flash/modify.md): `luma-photon/flash/modify`. $0.005 / run (estimated per run). - [Luma Photon · Modify](https://doitong.com/developers/models/luma-photon/modify.md): `luma-photon/modify`. $0.019 / run (estimated per run). - Luma Uni-1 (Luma AI), from $0.045: - [Luma Uni-1 Edit](https://doitong.com/developers/models/luma/agent/uni-1/v1/edit.md): `luma/agent/uni-1/v1/edit`. $0.045 / run. - [Luma Uni-1 Edit Max](https://doitong.com/developers/models/luma/agent/uni-1/v1/max/edit.md): `luma/agent/uni-1/v1/max/edit`. $0.105 / run. - [Mai Image 2.5](https://doitong.com/developers/models/microsoft/mai-image-2.5/edit.md): `microsoft/mai-image-2.5/edit`. Standard MAI Image 2.5 editor taking exactly one input image plus an edit instruction. $0.057 / image (estimated per run). - [MAI Image 2.5 Pro (Edit)](https://doitong.com/developers/models/microsoft/mai-image-2.5-pro/edit.md): `microsoft/mai-image-2.5-pro/edit`. Pro editing model that changes a single image from an instruction while keeping its layout and text. $0.179 / image (estimated per run). - [Minimax Image Subject Reference](https://doitong.com/developers/models/minimax/image-01/subject-reference.md): `minimax/image-01/subject-reference`. Image generation that keeps a character's look consistent using one subject reference image. $0.01 / image. - [Nano Banana · Edit](https://doitong.com/developers/models/nano-banana/edit.md): `nano-banana/edit`. Edits or combines input images following a text instruction, with an auto aspect ratio option. $0.0398 / image. - [Nano Banana Lite Edit](https://doitong.com/developers/models/google/nano-banana-lite/edit.md): `google/nano-banana-lite/edit`. Lite Nano Banana variant for prompt-based editing of one or more input images. $0.043 / image (estimated per run). - Phota (Open model), from $0.09: - [Phota](https://doitong.com/developers/models/phota/edit.md): `phota/edit`. from $0.09 / image. - [Phota Enhance](https://doitong.com/developers/models/phota/enhance.md): `phota/enhance`. $0.13 / image. - Playground v2.5 (Playground), from $0.004: - [Playground v2.5 · Image to Image](https://doitong.com/developers/models/playground-v25/image-to-image.md): `playground-v25/image-to-image`. $0.018 / image (estimated per run). - [Playground v2.5 · Inpainting](https://doitong.com/developers/models/playground-v25/inpainting.md): `playground-v25/inpainting`. $0.004 / image (estimated per run). - [Qwen Image · Image to Image](https://doitong.com/developers/models/qwen-image/image-to-image.md): `qwen-image/image-to-image`. Qwen Image restyling of a reference image, steered by a prompt and a denoising strength. $0.04 / image (estimated per run). - SDXL ControlNet Union (Stability AI), from $0.012: - [SDXL ControlNet Union · Image to Image](https://doitong.com/developers/models/sdxl-controlnet-union/image-to-image.md): `sdxl-controlnet-union/image-to-image`. $0.048 / image (estimated per run). - [SDXL ControlNet Union · Inpainting](https://doitong.com/developers/models/sdxl-controlnet-union/inpainting.md): `sdxl-controlnet-union/inpainting`. $0.012 / image (estimated per run). - [Stable Diffusion V3 · Image to Image](https://doitong.com/developers/models/stable-diffusion-v3-medium/image-to-image.md): `stable-diffusion-v3-medium/image-to-image`. Stable Diffusion 3 Medium image-to-image that restyles a source picture using a prompt and strength. $0.035 / image. - Stable Diffusion with LoRAs (Open model), from $0.184: - [Stable Diffusion with LoRAs · Image to Image](https://doitong.com/developers/models/lora/image-to-image.md): `lora/image-to-image`. $0.264 / image (estimated per run). - [Stable Diffusion with LoRAs · Inpaint](https://doitong.com/developers/models/lora/inpaint.md): `lora/inpaint`. $0.184 / image (estimated per run). - Stable Diffusion XL (Stability AI), from $0.008: - [Stable Diffusion XL · Image to Image](https://doitong.com/developers/models/fast-sdxl/image-to-image.md): `fast-sdxl/image-to-image`. $0.008 / image (estimated per run). - [Stable Diffusion XL · Inpainting](https://doitong.com/developers/models/fast-sdxl/inpainting.md): `fast-sdxl/inpainting`. $0.008 / image (estimated per run). - Stable Diffusion XL Lightning (Stability AI), from $0.005: - [Stable Diffusion XL Lightning · Image to Image](https://doitong.com/developers/models/fast-lightning-sdxl/image-to-image.md): `fast-lightning-sdxl/image-to-image`. $0.005 / image (estimated per run). - [Stable Diffusion XL Lightning · Inpainting](https://doitong.com/developers/models/fast-lightning-sdxl/inpainting.md): `fast-lightning-sdxl/inpainting`. $0.007 / image (estimated per run). - [Vecglypher · Image to SVG](https://doitong.com/developers/models/vecglypher/image-to-svg.md): `vecglypher/image-to-svg`. Generates SVG glyphs in the style of 1 to 8 reference glyph images instead of a text style description. $0.005 / image. - [Vidu · Q2 · Reference to Image](https://doitong.com/developers/models/vidu/q2/reference-to-image.md): `vidu/q2/reference-to-image`. Q2 image generator that combines reference images with a prompt to keep subjects consistent. $0.10 / image. - [Wan 2.5 Image to Image](https://doitong.com/developers/models/wan-25-preview/image-to-image.md): `wan-25-preview/image-to-image`. Wan 2.5 image editing from a text instruction, with one or two reference images. $0.05 / image. - Z Image Turbo (Alibaba), from $0.009: - [Z Image Turbo Controlnet](https://doitong.com/developers/models/z-image/turbo/controlnet.md): `z-image/turbo/controlnet`. $0.013 / image (estimated per run). - [Z Image Turbo Controlnet Lora](https://doitong.com/developers/models/z-image/turbo/controlnet/lora.md): `z-image/turbo/controlnet/lora`. $0.04 / image (estimated per run). - [Z Image Turbo Image To Image](https://doitong.com/developers/models/z-image/turbo/image-to-image.md): `z-image/turbo/image-to-image`. $0.015 / image (estimated per run). - [Z Image Turbo Image To Image Lora](https://doitong.com/developers/models/z-image/turbo/image-to-image/lora.md): `z-image/turbo/image-to-image/lora`. $0.009 / image (estimated per run). - [Z Image Turbo Inpaint](https://doitong.com/developers/models/z-image/turbo/inpaint.md): `z-image/turbo/inpaint`. $0.03 / image (estimated per run). - [Z Image Turbo Inpaint Lora](https://doitong.com/developers/models/z-image/turbo/inpaint/lora.md): `z-image/turbo/inpaint/lora`. $0.035 / image (estimated per run). - FLUX.1 Kontext (Black Forest Labs), from $0.025: - [FLUX.1 Kontext \[dev\]](https://doitong.com/developers/models/flux-kontext/dev.md): `flux-kontext/dev`. $0.025 / image (estimated per run). - [FLUX.1 Kontext \[max\]](https://doitong.com/developers/models/flux-pro/kontext/max.md): `flux-pro/kontext/max`. $0.08 / image. - [FLUX.1 Kontext \[pro\]](https://doitong.com/developers/models/flux-pro/kontext.md): `flux-pro/kontext`. $0.04 / image. - [FLUX.1 Kontext · Max · Multi](https://doitong.com/developers/models/flux-pro/kontext/max/multi.md): `flux-pro/kontext/max/multi`. $0.08 / image. - [FLUX.1 Kontext · Max · Text to Image](https://doitong.com/developers/models/flux-pro/kontext/max/text-to-image.md): `flux-pro/kontext/max/text-to-image`. $0.08 / image. - [FLUX.1 Kontext · Multi](https://doitong.com/developers/models/flux-pro/kontext/multi.md): `flux-pro/kontext/multi`. $0.04 / image. - [FLUX.1 Kontext · Text to Image](https://doitong.com/developers/models/flux-pro/kontext/text-to-image.md): `flux-pro/kontext/text-to-image`. $0.04 / image. - [Qwen Image 3 Edit](https://doitong.com/developers/models/alibaba/qwen-image-3/edit.md): `alibaba/qwen-image-3/edit`. Edit with one to three reference images, strong at changing or adding text in a picture. from $0.04 / image. - [Bernini-R Edit Image](https://doitong.com/developers/models/bernini-r/edit-image.md): `bernini-r/edit-image`. Edits an image from a natural-language instruction while keeping the original composition. $0.03 / megapixel of output image. - Bria (Bria AI), from $0.02: - [Bria](https://doitong.com/developers/models/bria/reimagine.md): `bria/reimagine`. $0.04 / image. - [Bria Background Replace](https://doitong.com/developers/models/bria/background/replace.md): `bria/background/replace`. $0.04 / image. - [Bria Eraser](https://doitong.com/developers/models/bria/eraser.md): `bria/eraser`. $0.04 / request. - [Bria Expand Image](https://doitong.com/developers/models/bria/expand.md): `bria/expand`. $0.04 / request. - [Bria GenFill](https://doitong.com/developers/models/bria/genfill.md): `bria/genfill`. $0.04 / image. - [Bria Product Dimensions](https://doitong.com/developers/models/bria/product-dimensions.md): `bria/product-dimensions`. $0.04 / image. - [Bria Product Shot](https://doitong.com/developers/models/bria/product-shot.md): `bria/product-shot`. $0.04 / image. - [Embed Product](https://doitong.com/developers/models/bria/embed-product.md): `bria/embed-product`. $0.04 / image. - [Extract Object](https://doitong.com/developers/models/bria/extract-object.md): `bria/extract-object`. $0.02 / image. - [Genfill](https://doitong.com/developers/models/bria/genfill/v2.md): `bria/genfill/v2`. $0.04 / run (estimated per run). - [Replace Background](https://doitong.com/developers/models/bria/replace-background.md): `bria/replace-background`. $0.04 / image. - Bria Fibo Edit 1.5 (Bria AI), from $0.04: - [Bria Expand (FIBO-Edit-1.5)](https://doitong.com/developers/models/bria/fibo-edit-1.5/expand.md): `bria/fibo-edit-1.5/expand`. $0.04 / image. - [Bria Product Holding (FIBO-Edit-1.5)](https://doitong.com/developers/models/bria/fibo-edit-1.5/product-holding.md): `bria/fibo-edit-1.5/product-holding`. $0.04 / image. - [Bria Virtual Try-On (FIBO-Edit-1.5)](https://doitong.com/developers/models/bria/fibo-edit-1.5/virtual-try-on.md): `bria/fibo-edit-1.5/virtual-try-on`. $0.04 / image. - [Fibo Edit 1.5 Image Editing](https://doitong.com/developers/models/bria/fibo-edit-1.5/edit.md): `bria/fibo-edit-1.5/edit`. $0.04 / image. - [Bytedance Seedream V4 Edit](https://doitong.com/developers/models/bytedance/seedream/v4/edit.md): `bytedance/seedream/v4/edit`. Prompt-based editing of up to 10 input images, with multi-image output and fast or standard prompt enhancement. $0.03 / image. - [Bytedance Seedream V4.5 Edit](https://doitong.com/developers/models/bytedance/seedream/v4.5/edit.md): `bytedance/seedream/v4.5/edit`. Edits one or more reference images from a text instruction, up to 10 inputs, with 2K/4K output sizes. $0.04 / image. - [Cartoonify](https://doitong.com/developers/models/cartoonify.md): `cartoonify`. Restyles a photo as 3D cartoon artwork while keeping its composition. $0.10 / image. - [try-on](https://doitong.com/developers/models/cat-vton.md): `cat-vton`. Virtual try-on that puts a garment image onto a person photo, with selectable clothing type. $0.018 / run (estimated per run). - [Chrono Edit](https://doitong.com/developers/models/chrono-edit.md): `chrono-edit`. Instruction-based image editor with optional temporal reasoning and turbo mode, output at 480p or 720p. from $0.01 / image. - [Chrono Edit Lora](https://doitong.com/developers/models/chrono-edit-lora.md): `chrono-edit-lora`. Chrono Edit variant that accepts up to 3 extra LoRAs merged into each edit request. from $0.02 / image. - [CodeFormer](https://doitong.com/developers/models/codeformer.md): `codeformer`. Face restoration model that repairs blurred or distorted portraits, with optional face alignment and upscaling. $0.0021 / megapixel of output image. - [ControlLight](https://doitong.com/developers/models/control-light.md): `control-light`. Low-light image enhancer with a single lighting_level slider from subtle to full brightening. $0.06 / run (estimated per run). - [DDColor](https://doitong.com/developers/models/ddcolor.md): `ddcolor`. Colorizes black-and-white photos from a single image input. $0.003 / run (estimated per run). - Docres (Open model), from $0.025: - [DocRes](https://doitong.com/developers/models/docres.md): `docres`. $0.025 / run (estimated per run). - [DocRes-dewarp](https://doitong.com/developers/models/docres/dewarp.md): `docres/dewarp`. $0.03 / run (estimated per run). - [DreamOmni2](https://doitong.com/developers/models/dreamomni2/edit.md): `dreamomni2/edit`. Edits one or more input images by following a text instruction, using image URLs plus a prompt. $0.05 / image. - [DWPose Pose Prediction](https://doitong.com/developers/models/dwpose.md): `dwpose`. Detects human pose in an image and draws it as a body, face, hand or mask map. $0.001 / run (estimated per run). - [Emu 3.5 Image · Edit Image](https://doitong.com/developers/models/emu-3.5-image/edit-image.md): `emu-3.5-image/edit-image`. Edits an input image from a text prompt, with 480p or 720p output and an auto aspect ratio option. from $0.15 / image. - [EVF-SAM2 Segmentation](https://doitong.com/developers/models/evf-sam.md): `evf-sam`. Text-guided image segmentation that returns masks from positive and negative prompts. from $0.005 / request. - [Face Retoucher](https://doitong.com/developers/models/retoucher.md): `retoucher`. Smooths skin and removes blemishes on faces in a photo from a single image URL. $0.173 / run (estimated per run). - FASHN Virtual Try-On (FASHN), from $0.075: - [FASHN Virtual Try-On V1.5](https://doitong.com/developers/models/fashn/tryon/v1.5.md): `fashn/tryon/v1.5`. $0.075 / image. - [FASHN Virtual Try-On V1.6](https://doitong.com/developers/models/fashn/tryon/v1.6.md): `fashn/tryon/v1.6`. $0.075 / image. - [Fibo 2.0 Edit](https://doitong.com/developers/models/bria/fibo-2/edit.md): `bria/fibo-2/edit`. Instruction-based editor taking 1 to 4 images, with optional mask for single-image regional edits. $0.04 / image. - Fibo Edit (Bria AI), from $0.04: - [Fibo Edit](https://doitong.com/developers/models/bria/fibo-edit/edit.md): `bria/fibo-edit/edit`. $0.04 / image. - [Fibo Edit \[Add Object by Text\]](https://doitong.com/developers/models/bria/fibo-edit/add_object_by_text.md): `bria/fibo-edit/add_object_by_text`. $0.04 / image. - [Fibo Edit \[Blend\]](https://doitong.com/developers/models/bria/fibo-edit/blend.md): `bria/fibo-edit/blend`. $0.04 / image. - [Fibo Edit \[Colorize\]](https://doitong.com/developers/models/bria/fibo-edit/colorize.md): `bria/fibo-edit/colorize`. $0.04 / image. - [Fibo Edit \[Erase by Text\]](https://doitong.com/developers/models/bria/fibo-edit/erase_by_text.md): `bria/fibo-edit/erase_by_text`. $0.04 / image. - [Fibo Edit \[Relight\]](https://doitong.com/developers/models/bria/fibo-edit/relight.md): `bria/fibo-edit/relight`. $0.04 / image. - [Fibo Edit \[Replace Object by Text\]](https://doitong.com/developers/models/bria/fibo-edit/replace_object_by_text.md): `bria/fibo-edit/replace_object_by_text`. $0.04 / image. - [Fibo Edit \[Reseason\]](https://doitong.com/developers/models/bria/fibo-edit/reseason.md): `bria/fibo-edit/reseason`. $0.04 / image. - [Fibo Edit \[Restore\]](https://doitong.com/developers/models/bria/fibo-edit/restore.md): `bria/fibo-edit/restore`. $0.04 / image. - [Fibo Edit \[Restyle\]](https://doitong.com/developers/models/bria/fibo-edit/restyle.md): `bria/fibo-edit/restyle`. $0.04 / image. - [Fibo Edit \[Rewrite Text\]](https://doitong.com/developers/models/bria/fibo-edit/rewrite_text.md): `bria/fibo-edit/rewrite_text`. $0.04 / image. - [Fibo Edit \[Sketch to Image\]](https://doitong.com/developers/models/bria/fibo-edit/sketch_to_colored_image.md): `bria/fibo-edit/sketch_to_colored_image`. $0.04 / image. - Finegrain Eraser (Finegrain), from $0.04: - [Finegrain Eraser](https://doitong.com/developers/models/finegrain-eraser.md): `finegrain-eraser`. from $0.18 / image. - [Finegrain Eraser Bbox](https://doitong.com/developers/models/finegrain-eraser/bbox.md): `finegrain-eraser/bbox`. from $0.09 / image. - [Finegrain Eraser Mask](https://doitong.com/developers/models/finegrain-eraser/mask.md): `finegrain-eraser/mask`. from $0.04 / image. - [Firered Image Edit](https://doitong.com/developers/models/firered-image-edit.md): `firered-image-edit`. Instruction-based image editor that accepts several reference images and English or Chinese prompts. $0.033 / image (estimated per run). - [Firered Image Edit V1.1](https://doitong.com/developers/models/firered-image-edit-v1.1.md): `firered-image-edit-v1.1`. Updated FireRed editor, with portrait makeup added to its multi-reference editing uses. $0.065 / image (estimated per run). - [Flow-Edit](https://doitong.com/developers/models/flowedit.md): `flowedit`. Edits an image by contrasting a source prompt with a target prompt, with fine control over edit strength. $0.04 / run (estimated per run). - [Flux 3 Image · Edit Image](https://doitong.com/developers/models/blackforestlabs/flux-3/edit-image.md): `blackforestlabs/flux-3/edit-image`. FLUX 3 image editor that makes local edits and merges up to 10 reference images. from $0.048 / megapixel. - Flux Kontext Lora (Black Forest Labs), from $0.035: - [Flux Kontext Lora](https://doitong.com/developers/models/flux-kontext-lora.md): `flux-kontext-lora`. $0.07 / image (estimated per run). - [Flux Kontext Lora · Inpaint](https://doitong.com/developers/models/flux-kontext-lora/inpaint.md): `flux-kontext-lora/inpaint`. $0.035 / image (estimated per run). - Flux Pro v1 (Black Forest Labs), from $0.042: - [Flux Pro Erase](https://doitong.com/developers/models/flux-pro/v1/erase.md): `flux-pro/v1/erase`. from $0.042 / run. - [FLUX Virtual Try-On](https://doitong.com/developers/models/flux-pro/v1/vto.md): `flux-pro/v1/vto`. from $0.0475 / run. - [FLUX.1 \[dev\] Canny with LoRAs](https://doitong.com/developers/models/flux-lora-canny.md): `flux-lora-canny`. FLUX.1 [dev] Canny edge control with LoRAs for composition-guided generation. $0.07 / image (estimated per run). - [FLUX.1 \[dev\] Depth with LoRAs](https://doitong.com/developers/models/flux-lora-depth.md): `flux-lora-depth`. FLUX.1 [dev] depth-conditioned generation with LoRAs, keeping scene layout. $0.07 / image (estimated per run). - [FLUX.1 \[dev\] Fill with LoRAs](https://doitong.com/developers/models/flux-lora-fill.md): `flux-lora-fill`. Fill-style inpainting with LoRAs, optional reference image for the masked area and paste-back control. $0.07 / image (estimated per run). - [FLUX.3 Klein Image Editing](https://doitong.com/developers/models/blackforestlabs/flux-3/klein/edit-image.md): `blackforestlabs/flux-3/klein/edit-image`. FLUX.3 Klein editor with up to 10 references and optional bounding-box object placement. from $0.008 / run of output image. - [Ghiblify Images](https://doitong.com/developers/models/ghiblify.md): `ghiblify`. Restyles a photo into Studio Ghibli-like artwork from a single image URL. $0.05 / image. - [gpt-image-1 · Edit Image](https://doitong.com/developers/models/gpt-image-1/edit-image.md): `gpt-image-1/edit-image`. Edits or combines reference images with a prompt, with an input fidelity setting and transparent background option. from $0.011 / run of output image. - [Grok Imagine Image 2.0 · Edit](https://doitong.com/developers/models/xai/grok-imagine-image/v2.0/edit.md): `xai/grok-imagine-image/v2.0/edit`. Prompt-driven editing of up to 5 input images, with 1k or 2k output and many aspect ratios including auto. from $0.04 / run of output image. - [Hidream O1 Image · Dev · Edit](https://doitong.com/developers/models/hidream-o1-image/dev/edit.md): `hidream-o1-image/dev/edit`. Distilled dev variant of reference-image editing, 28 steps and guidance 0 by default. $0.005 / megapixel. - [Hunyuan Image · v3 · Instruct · Edit](https://doitong.com/developers/models/hunyuan-image/v3/instruct/edit.md): `hunyuan-image/v3/instruct/edit`. Instruction-based image editing from up to 3 reference images, with optional prompt expansion. $0.174 / image (estimated per run). - [Hunyuan World](https://doitong.com/developers/models/hunyuan_world.md): `hunyuan_world`. Converts a single image and prompt into a panorama image. $0.15 / image. - [Hy Wu Edit](https://doitong.com/developers/models/hy-wu-edit.md): `hy-wu-edit`. Reference-guided image editor for outfit transfer, face swaps and texture blending from 2-3 input images. from $0.10 / image. - [IC-Light-v2 for Image Relighting](https://doitong.com/developers/models/iclight-v2.md): `iclight-v2`. Relights a photo and changes its background according to a text description. $0.40 / image (estimated per run). - Ideogram V3 Character (Ideogram), from $0.10: - [Ideogram V3 Character](https://doitong.com/developers/models/ideogram/character.md): `ideogram/character`. from $0.10 / image. - [Ideogram V3 Character Edit](https://doitong.com/developers/models/ideogram/character/edit.md): `ideogram/character/edit`. from $0.10 / image. - [Ideogram V3 Character Remix](https://doitong.com/developers/models/ideogram/character/remix.md): `ideogram/character/remix`. from $0.10 / image. - Image Apps v2 (Utility), from $0.04: - [Age Modify](https://doitong.com/developers/models/image-apps-v2/age-modify.md): `image-apps-v2/age-modify`. $0.04 / image. - [City Teleport](https://doitong.com/developers/models/image-apps-v2/city-teleport.md): `image-apps-v2/city-teleport`. $0.04 / image. - [Expression Change](https://doitong.com/developers/models/image-apps-v2/expression-change.md): `image-apps-v2/expression-change`. $0.04 / image. - [Hair Change](https://doitong.com/developers/models/image-apps-v2/hair-change.md): `image-apps-v2/hair-change`. $0.04 / image. - [Headshot Generator](https://doitong.com/developers/models/image-apps-v2/headshot-photo.md): `image-apps-v2/headshot-photo`. $0.04 / image. - [Image Outpaint](https://doitong.com/developers/models/image-apps-v2/outpaint.md): `image-apps-v2/outpaint`. $0.07 / image (estimated per run). - [Makeup Changer](https://doitong.com/developers/models/image-apps-v2/makeup-application.md): `image-apps-v2/makeup-application`. $0.04 / image. - [Object Removal · Image Apps v2](https://doitong.com/developers/models/image-apps-v2/object-removal.md): `image-apps-v2/object-removal`. $0.04 / image. - [Perspective Change](https://doitong.com/developers/models/image-apps-v2/perspective.md): `image-apps-v2/perspective`. $0.04 / image. - [Photo Restoration](https://doitong.com/developers/models/image-apps-v2/photo-restoration.md): `image-apps-v2/photo-restoration`. $0.04 / image. - [Photography Effects](https://doitong.com/developers/models/image-apps-v2/photography-effects.md): `image-apps-v2/photography-effects`. $0.40 / image. - [Portrait Enhance](https://doitong.com/developers/models/image-apps-v2/portrait-enhance.md): `image-apps-v2/portrait-enhance`. $0.40 / image. - [Product Holding](https://doitong.com/developers/models/image-apps-v2/product-holding.md): `image-apps-v2/product-holding`. $0.04 / image. - [Product Photography](https://doitong.com/developers/models/image-apps-v2/product-photography.md): `image-apps-v2/product-photography`. $0.04 / image. - [Relighting](https://doitong.com/developers/models/image-apps-v2/relighting.md): `image-apps-v2/relighting`. $0.04 / image. - [Style Transfer](https://doitong.com/developers/models/image-apps-v2/style-transfer.md): `image-apps-v2/style-transfer`. $0.04 / image. - [Texture Transform](https://doitong.com/developers/models/image-apps-v2/texture-transform.md): `image-apps-v2/texture-transform`. $0.04 / image. - [Virtual Try-on](https://doitong.com/developers/models/image-apps-v2/virtual-try-on.md): `image-apps-v2/virtual-try-on`. $0.04 / image. - Image Editing (Utility), from $0.04: - [Image Editing](https://doitong.com/developers/models/image-editing/baby-version.md): `image-editing/baby-version`. $0.04 / image. - [Image Editing Age Progression](https://doitong.com/developers/models/image-editing/age-progression.md): `image-editing/age-progression`. $0.04 / image. - [Image Editing Background Change](https://doitong.com/developers/models/image-editing/background-change.md): `image-editing/background-change`. $0.04 / image. - [Image Editing Broccoli Haircut](https://doitong.com/developers/models/image-editing/broccoli-haircut.md): `image-editing/broccoli-haircut`. $0.04 / image. - [Image Editing Cartoonify](https://doitong.com/developers/models/image-editing/cartoonify.md): `image-editing/cartoonify`. $0.04 / image. - [Image Editing Color Correction](https://doitong.com/developers/models/image-editing/color-correction.md): `image-editing/color-correction`. $0.04 / image. - [Image Editing Expression Change](https://doitong.com/developers/models/image-editing/expression-change.md): `image-editing/expression-change`. $0.04 / image. - [Image Editing Face Enhancement](https://doitong.com/developers/models/image-editing/face-enhancement.md): `image-editing/face-enhancement`. $0.04 / image. - [Image Editing Hair Change](https://doitong.com/developers/models/image-editing/hair-change.md): `image-editing/hair-change`. $0.04 / image. - [Image Editing Object Removal](https://doitong.com/developers/models/image-editing/object-removal.md): `image-editing/object-removal`. $0.04 / image. - [Image Editing Photo Restoration](https://doitong.com/developers/models/image-editing/photo-restoration.md): `image-editing/photo-restoration`. $0.04 / image. - [Image Editing Plushie Style](https://doitong.com/developers/models/image-editing/plushie-style.md): `image-editing/plushie-style`. $0.04 / image. - [Image Editing Professional Photo](https://doitong.com/developers/models/image-editing/professional-photo.md): `image-editing/professional-photo`. $0.04 / image. - [Image Editing Realism](https://doitong.com/developers/models/image-editing/realism.md): `image-editing/realism`. $0.04 / image. - [Image Editing Reframe](https://doitong.com/developers/models/image-editing/reframe.md): `image-editing/reframe`. $0.04 / image. - [Image Editing Retouch](https://doitong.com/developers/models/image-editing/retouch.md): `image-editing/retouch`. $0.04 / image. - [Image Editing Scene Composition](https://doitong.com/developers/models/image-editing/scene-composition.md): `image-editing/scene-composition`. $0.04 / image. - [Image Editing Style Transfer](https://doitong.com/developers/models/image-editing/style-transfer.md): `image-editing/style-transfer`. $0.04 / image. - [Image Editing Text Removal](https://doitong.com/developers/models/image-editing/text-removal.md): `image-editing/text-removal`. $0.04 / image. - [Image Editing Time Of Day](https://doitong.com/developers/models/image-editing/time-of-day.md): `image-editing/time-of-day`. $0.04 / image. - [Image Editing Weather Effect](https://doitong.com/developers/models/image-editing/weather-effect.md): `image-editing/weather-effect`. $0.04 / image. - [Image Editing Wojak Style](https://doitong.com/developers/models/image-editing/wojak-style.md): `image-editing/wojak-style`. $0.04 / image. - [Image Editing Youtube Thumbnails](https://doitong.com/developers/models/image-editing/youtube-thumbnails.md): `image-editing/youtube-thumbnails`. $0.04 / image. - Image Preprocessors (Utility), from $0.003: - [Image Preprocessors · Depth Anything · v2](https://doitong.com/developers/models/image-preprocessors/depth-anything/v2.md): `image-preprocessors/depth-anything/v2`. $0.004 / run (estimated per run). - [Image Preprocessors · Hed](https://doitong.com/developers/models/image-preprocessors/hed.md): `image-preprocessors/hed`. $0.003 / run (estimated per run). - [Image Preprocessors · Lineart](https://doitong.com/developers/models/image-preprocessors/lineart.md): `image-preprocessors/lineart`. $0.003 / run (estimated per run). - [Image Preprocessors · Midas](https://doitong.com/developers/models/image-preprocessors/midas.md): `image-preprocessors/midas`. $0.008 / run (estimated per run). - [Image Preprocessors · Mlsd](https://doitong.com/developers/models/image-preprocessors/mlsd.md): `image-preprocessors/mlsd`. $0.004 / run (estimated per run). - [Image Preprocessors · Pidi](https://doitong.com/developers/models/image-preprocessors/pidi.md): `image-preprocessors/pidi`. $0.008 / run (estimated per run). - [Image Preprocessors · SAM](https://doitong.com/developers/models/image-preprocessors/sam.md): `image-preprocessors/sam`. $0.006 / run (estimated per run). - [Image Preprocessors · Scribble](https://doitong.com/developers/models/image-preprocessors/scribble.md): `image-preprocessors/scribble`. $0.004 / run (estimated per run). - [Image Preprocessors · Teed](https://doitong.com/developers/models/image-preprocessors/teed.md): `image-preprocessors/teed`. $0.003 / run (estimated per run). - [Image Preprocessors · Zoe](https://doitong.com/developers/models/image-preprocessors/zoe.md): `image-preprocessors/zoe`. $0.02 / run (estimated per run). - [Image2Pixel](https://doitong.com/developers/models/image2pixel.md): `image2pixel`. Converts images to clean pixel art with palette limits, scale detection, and optional transparent background. $0.00017 / second of processing time (charged by usage, up to $0.153 per run for the example input; the rest is refunded). - [Image2svg](https://doitong.com/developers/models/image2svg.md): `image2svg`. Vectorizes a raster image into an SVG with color or binary mode and spline or polygon paths. $0.005 / image. - [Inpainting sdxl and sd](https://doitong.com/developers/models/inpaint.md): `inpaint`. Inpaints masked regions of an image using any chosen SD or SDXL base model. $0.029 / run (estimated per run). - [Instant Character](https://doitong.com/developers/models/instant-character.md): `instant-character`. Generates new images of a character from a reference image and prompt while keeping identity. $0.10 / megapixel. - [IP Adapter Face ID](https://doitong.com/developers/models/ip-adapter-face-id.md): `ip-adapter-face-id`. Generates images that match a face from one photo or a zip of photos, on SD 1.5 or SDXL bases. $0.015 / image (estimated per run). - [Joyai Image Edit](https://doitong.com/developers/models/joyai-image-edit.md): `joyai-image-edit`. Instruction-based editing of a single image with negative prompt, step, and guidance controls. $0.10 / run (estimated per run). - [Juggernaut Flux Lora](https://doitong.com/developers/models/rundiffusion/juggernaut-flux-lora/inpainting.md): `rundiffusion/juggernaut-flux-lora/inpainting`. Juggernaut Flux inpainting with a mask and LoRA support. $0.045 / image (estimated per run). - [Kling O1 Image](https://doitong.com/developers/models/kling-image/o1.md): `kling-image/o1`. Reference-driven image editing with up to 10 images, @Image tags and elements, 1K or 2K, up to 9 outputs. $0.028 / image. - [Krea 3 Edit](https://doitong.com/developers/models/krea/v3/edit.md): `krea/v3/edit`. Krea 3 image editing that edits or combines 1 to 8 reference images from text instructions. $0.026 / run (estimated per run). - Leffa (Meta), from $0.10: - [Leffa Pose Transfer](https://doitong.com/developers/models/leffa/pose-transfer.md): `leffa/pose-transfer`. $0.10 / request. - [Leffa Virtual TryOn](https://doitong.com/developers/models/leffa/virtual-tryon.md): `leffa/virtual-tryon`. $0.10 / request. - [Marigold V2 Depth](https://doitong.com/developers/models/marigold-v2.md): `marigold-v2`. Image analysis model that outputs depth, see-through depth, normals or albedo maps from one image. $0.03 / image. - [Meta Muse Image Edit](https://doitong.com/developers/models/meta/muse-image/edit.md): `meta/muse-image/edit`. Instruction-based image editing with up to 10 reference images and custom aspect ratios. $0.01 / image. - Nafnet (Open model), from $0.023: - [NAFNet-deblur](https://doitong.com/developers/models/nafnet/deblur.md): `nafnet/deblur`. $0.023 / run (estimated per run). - [NAFNet-denoise](https://doitong.com/developers/models/nafnet/denoise.md): `nafnet/denoise`. $0.023 / run (estimated per run). - Object Removal (Utility), from $0.006: - [Object Removal](https://doitong.com/developers/models/object-removal.md): `object-removal`. from $0.006 / image. - [Object Removal · Bbox](https://doitong.com/developers/models/object-removal/bbox.md): `object-removal/bbox`. from $0.006 / image. - [Object Removal · Mask](https://doitong.com/developers/models/object-removal/mask.md): `object-removal/mask`. from $0.006 / image. - [Omni Zero](https://doitong.com/developers/models/omni-zero.md): `omni-zero`. Combines separate composition, style and identity reference images into one new image. $0.073 / image (estimated per run). - [Optimized Latent Consistency (SDv1.5)](https://doitong.com/developers/models/lcm-sd15-i2i.md): `lcm-sd15-i2i`. Few-step image-to-image transform on Stable Diffusion 1.5 using latent consistency, with strength control. $0.007 / image (estimated per run). - [PASD](https://doitong.com/developers/models/pasd.md): `pasd`. Diffusion-based super-resolution that upscales images 1x to 4x with optional prompt guidance. $0.03 / megapixel of output image. - Patina (Open model), from $0.023: - [PATINA](https://doitong.com/developers/models/patina.md): `patina`. from $0.0225 / run of input image. - [PATINA · Material · Extract](https://doitong.com/developers/models/patina/material/extract.md): `patina/material/extract`. from $0.17 / run. - [PhotoMaker](https://doitong.com/developers/models/photomaker.md): `photomaker`. Personalized portrait generation from an archive of reference photos, with style presets and optional img2img. $0.022 / image (estimated per run). - Post Processing (Utility), from $0.001: - [Post Processing](https://doitong.com/developers/models/post-processing.md): `post-processing`. $0.001 / request. - [Post Processing Blur](https://doitong.com/developers/models/post-processing/blur.md): `post-processing/blur`. $0.001 / image. - [Post Processing Chromatic Aberration](https://doitong.com/developers/models/post-processing/chromatic-aberration.md): `post-processing/chromatic-aberration`. $0.001 / image. - [Post Processing Color Correction](https://doitong.com/developers/models/post-processing/color-correction.md): `post-processing/color-correction`. $0.001 / image. - [Post Processing Color Tint](https://doitong.com/developers/models/post-processing/color-tint.md): `post-processing/color-tint`. $0.001 / image. - [Post Processing Desaturate](https://doitong.com/developers/models/post-processing/desaturate.md): `post-processing/desaturate`. $0.001 / image. - [Post Processing Dissolve](https://doitong.com/developers/models/post-processing/dissolve.md): `post-processing/dissolve`. $0.001 / image. - [Post Processing Dodge Burn](https://doitong.com/developers/models/post-processing/dodge-burn.md): `post-processing/dodge-burn`. $0.001 / image. - [Post Processing Grain](https://doitong.com/developers/models/post-processing/grain.md): `post-processing/grain`. $0.001 / image. - [Post Processing Parabolize](https://doitong.com/developers/models/post-processing/parabolize.md): `post-processing/parabolize`. $0.001 / image. - [Post Processing Sharpen](https://doitong.com/developers/models/post-processing/sharpen.md): `post-processing/sharpen`. $0.001 / image. - [Post Processing Solarize](https://doitong.com/developers/models/post-processing/solarize.md): `post-processing/solarize`. $0.001 / image. - [Post Processing Vignette](https://doitong.com/developers/models/post-processing/vignette.md): `post-processing/vignette`. $0.001 / image. - [PuLID](https://doitong.com/developers/models/pulid.md): `pulid`. Generates new images that keep a person's face from reference photos, without per-person tuning. $0.009 / image (estimated per run). - [PuLID Flux](https://doitong.com/developers/models/flux-pulid.md): `flux-pulid`. Personalized generation that uses a reference face image plus a prompt, with adjustable identity weight. $0.0333 / megapixel. - Qwen Image Edit (Alibaba), from $0.03: - [Qwen Image Edit](https://doitong.com/developers/models/qwen-image-edit.md): `qwen-image-edit`. $0.03 / image (estimated per run). - [Qwen Image Edit · Image to Image](https://doitong.com/developers/models/qwen-image-edit/image-to-image.md): `qwen-image-edit/image-to-image`. $0.06 / image (estimated per run). - [Qwen Image Edit · Inpaint](https://doitong.com/developers/models/qwen-image-edit/inpaint.md): `qwen-image-edit/inpaint`. $0.03 / image (estimated per run). - [Qwen Image Edit 2509](https://doitong.com/developers/models/qwen-image-edit-2509.md): `qwen-image-edit-2509`. Multi-image Qwen edit model that takes a list of input images with a prompt. $0.03 / megapixel. - [Qwen Image Edit 2509 Lora](https://doitong.com/developers/models/qwen-image-edit-2509-lora.md): `qwen-image-edit-2509-lora`. Qwen Image Edit 2509 with LoRA loading for multi-image edits in custom styles. $0.07 / image (estimated per run). - Qwen Image Edit 2509 Lora Gallery (Alibaba), from $0.035: - [Qwen Image Edit 2509 Lora Gallery · Add Background](https://doitong.com/developers/models/qwen-image-edit-2509-lora-gallery/add-background.md): `qwen-image-edit-2509-lora-gallery/add-background`. $0.035 / image (estimated per run). - [Qwen Image Edit 2509 Lora Gallery · Face to Full Portrait](https://doitong.com/developers/models/qwen-image-edit-2509-lora-gallery/face-to-full-portrait.md): `qwen-image-edit-2509-lora-gallery/face-to-full-portrait`. $0.035 / image (estimated per run). - [Qwen Image Edit 2509 Lora Gallery · Group Photo](https://doitong.com/developers/models/qwen-image-edit-2509-lora-gallery/group-photo.md): `qwen-image-edit-2509-lora-gallery/group-photo`. $0.035 / image (estimated per run). - [Qwen Image Edit 2509 Lora Gallery · Integrate Product](https://doitong.com/developers/models/qwen-image-edit-2509-lora-gallery/integrate-product.md): `qwen-image-edit-2509-lora-gallery/integrate-product`. $0.035 / image (estimated per run). - [Qwen Image Edit 2509 Lora Gallery · Lighting Restoration](https://doitong.com/developers/models/qwen-image-edit-2509-lora-gallery/lighting-restoration.md): `qwen-image-edit-2509-lora-gallery/lighting-restoration`. $0.035 / image (estimated per run). - [Qwen Image Edit 2509 Lora Gallery · Multiple Angles](https://doitong.com/developers/models/qwen-image-edit-2509-lora-gallery/multiple-angles.md): `qwen-image-edit-2509-lora-gallery/multiple-angles`. $0.035 / image (estimated per run). - [Qwen Image Edit 2509 Lora Gallery · Next Scene](https://doitong.com/developers/models/qwen-image-edit-2509-lora-gallery/next-scene.md): `qwen-image-edit-2509-lora-gallery/next-scene`. $0.035 / image (estimated per run). - [Qwen Image Edit 2509 Lora Gallery · Remove Element](https://doitong.com/developers/models/qwen-image-edit-2509-lora-gallery/remove-element.md): `qwen-image-edit-2509-lora-gallery/remove-element`. $0.035 / image (estimated per run). - [Qwen Image Edit 2509 Lora Gallery · Remove Lighting](https://doitong.com/developers/models/qwen-image-edit-2509-lora-gallery/remove-lighting.md): `qwen-image-edit-2509-lora-gallery/remove-lighting`. $0.035 / image (estimated per run). - [Qwen Image Edit 2509 Lora Gallery · Shirt Design](https://doitong.com/developers/models/qwen-image-edit-2509-lora-gallery/shirt-design.md): `qwen-image-edit-2509-lora-gallery/shirt-design`. $0.035 / image (estimated per run). - Qwen Image Edit 2511 (Alibaba), from $0.07: - [Qwen Image Edit 2511](https://doitong.com/developers/models/qwen-image-edit-2511.md): `qwen-image-edit-2511`. $0.09 / image (estimated per run). - [Qwen Image Edit 2511 · LoRA](https://doitong.com/developers/models/qwen-image-edit-2511/lora.md): `qwen-image-edit-2511/lora`. $0.07 / image (estimated per run). - [Qwen Image Edit 2511 Multiple Angles](https://doitong.com/developers/models/qwen-image-edit-2511-multiple-angles.md): `qwen-image-edit-2511-multiple-angles`. Re-renders a scene from a new camera angle using horizontal, vertical and zoom controls. $0.035 / image (estimated per run). - [Qwen Image Edit Lora](https://doitong.com/developers/models/qwen-image-edit-lora.md): `qwen-image-edit-lora`. Single-image edit with the original Qwen Image Edit model plus up to 3 merged LoRAs. $0.035 / image (estimated per run). - [Qwen Image Edit Plus](https://doitong.com/developers/models/qwen-image-edit-plus.md): `qwen-image-edit-plus`. Multi-image editing model (Qwen-Image-Edit-2509) tuned for text edits, with up to 100 steps. $0.03 / megapixel. - [Qwen Image Edit Plus Lora](https://doitong.com/developers/models/qwen-image-edit-plus-lora.md): `qwen-image-edit-plus-lora`. Qwen Image Edit Plus with a `loras` input for merging up to 3 LoRAs on multi-image edits. $0.07 / image (estimated per run). - Qwen Image Edit Plus Lora Gallery (Alibaba), from $0.035: - [Qwen Image Edit Plus Lora Gallery · Add Background](https://doitong.com/developers/models/qwen-image-edit-plus-lora-gallery/add-background.md): `qwen-image-edit-plus-lora-gallery/add-background`. $0.035 / image (estimated per run). - [Qwen Image Edit Plus Lora Gallery · Face to Full Portrait](https://doitong.com/developers/models/qwen-image-edit-plus-lora-gallery/face-to-full-portrait.md): `qwen-image-edit-plus-lora-gallery/face-to-full-portrait`. $0.035 / image (estimated per run). - [Qwen Image Edit Plus Lora Gallery · Group Photo](https://doitong.com/developers/models/qwen-image-edit-plus-lora-gallery/group-photo.md): `qwen-image-edit-plus-lora-gallery/group-photo`. $0.035 / image (estimated per run). - [Qwen Image Edit Plus Lora Gallery · Integrate Product](https://doitong.com/developers/models/qwen-image-edit-plus-lora-gallery/integrate-product.md): `qwen-image-edit-plus-lora-gallery/integrate-product`. $0.035 / image (estimated per run). - [Qwen Image Edit Plus Lora Gallery · Lighting Restoration](https://doitong.com/developers/models/qwen-image-edit-plus-lora-gallery/lighting-restoration.md): `qwen-image-edit-plus-lora-gallery/lighting-restoration`. $0.035 / image (estimated per run). - [Qwen Image Edit Plus Lora Gallery · Multiple Angles](https://doitong.com/developers/models/qwen-image-edit-plus-lora-gallery/multiple-angles.md): `qwen-image-edit-plus-lora-gallery/multiple-angles`. $0.035 / image (estimated per run). - [Qwen Image Edit Plus Lora Gallery · Next Scene](https://doitong.com/developers/models/qwen-image-edit-plus-lora-gallery/next-scene.md): `qwen-image-edit-plus-lora-gallery/next-scene`. $0.035 / image (estimated per run). - [Qwen Image Edit Plus Lora Gallery · Remove Element](https://doitong.com/developers/models/qwen-image-edit-plus-lora-gallery/remove-element.md): `qwen-image-edit-plus-lora-gallery/remove-element`. $0.035 / image (estimated per run). - [Qwen Image Edit Plus Lora Gallery · Remove Lighting](https://doitong.com/developers/models/qwen-image-edit-plus-lora-gallery/remove-lighting.md): `qwen-image-edit-plus-lora-gallery/remove-lighting`. $0.035 / image (estimated per run). - [Qwen Image Edit Plus Lora Gallery · Shirt Design](https://doitong.com/developers/models/qwen-image-edit-plus-lora-gallery/shirt-design.md): `qwen-image-edit-plus-lora-gallery/shirt-design`. $0.035 / image (estimated per run). - Qwen Image Layered (Alibaba), from $0.20: - [Qwen Image Layered](https://doitong.com/developers/models/qwen-image-layered.md): `qwen-image-layered`. $0.05 / image. - [Qwen Image Layered · LoRA](https://doitong.com/developers/models/qwen-image-layered/lora.md): `qwen-image-layered/lora`. $0.06 / image. - [Qwen Image Max · Edit](https://doitong.com/developers/models/qwen-image-max/edit.md): `qwen-image-max/edit`. Edits with Qwen Image Max using 1 to 3 ordered reference images and bilingual prompts. $0.075 / image. - Recraft v3 (Recraft), from $0.01: - [Recraft](https://doitong.com/developers/models/recraft/vectorize.md): `recraft/vectorize`. $0.01 / image. - [Recraft V3 · Image to Image](https://doitong.com/developers/models/recraft/v3/image-to-image.md): `recraft/v3/image-to-image`. from $0.04 / image. - Sam 3 1 (Meta), from $0.01: - [Sam 3 1 · Image](https://doitong.com/developers/models/sam-3-1/image.md): `sam-3-1/image`. $0.01 / run (estimated per run). - [Sam 3 1 · Image RLE](https://doitong.com/developers/models/sam-3-1/image-rle.md): `sam-3-1/image-rle`. $0.01 / run (estimated per run). - Sam3 (Meta), from $0.005: - [Sam 3 · Image RLE](https://doitong.com/developers/models/sam-3/image-rle.md): `sam-3/image-rle`. $0.005 / run (estimated per run). - [Segment Anything Model 3](https://doitong.com/developers/models/sam-3/image.md): `sam-3/image`. $0.005 / run (estimated per run). - [Seedream · Flash · Edit](https://doitong.com/developers/models/bytedance/seedream/v5/flash/edit.md): `bytedance/seedream/v5/flash/edit`. Seedream 5 Flash image editing from a prompt and up to 10 reference images. $0.027 / image. - [Seedream · Lite · Edit](https://doitong.com/developers/models/bytedance/seedream/v5/lite/edit.md): `bytedance/seedream/v5/lite/edit`. Seedream 5 Lite image editing from up to 10 input images, with output sizes up to 4K tiers. $0.035 / image. - Segment Anything Model 2 (Meta), from $0.002: - [Segment Anything Model 2 · Auto Segment](https://doitong.com/developers/models/sam2/auto-segment.md): `sam2/auto-segment`. $0.014 / run (estimated per run). - [Segment Anything Model 2 · Image](https://doitong.com/developers/models/sam2/image.md): `sam2/image`. $0.002 / run (estimated per run). - [Smart Resize](https://doitong.com/developers/models/smart-resize.md): `smart-resize`. Recomposes an image to up to 10 target dimensions, useful for ad and crop variants. from $0.15 / run of output image. - [Stepx Edit2](https://doitong.com/developers/models/stepx-edit2.md): `stepx-edit2`. Instruction-based image editor with optional thinking and reflection passes for abstract edits. $0.20 / run (estimated per run). - [Telestyle V2 Style Transfer](https://doitong.com/developers/models/telestyle-v2.md): `telestyle-v2`. Style transfer that re-renders a content image using the look of a second style reference image. $0.071 / image (estimated per run). - [Topaz Adjust Image](https://doitong.com/developers/models/topaz/adjust/image.md): `topaz/adjust/image`. One-step photo correction for exposure, white balance, or colorizing black-and-white images. $0.08 / 24 megapixels of output image. - [Topaz Denoise Image](https://doitong.com/developers/models/topaz/denoise/image.md): `topaz/denoise/image`. Photo denoiser with Normal, Strong, Extreme presets and a generative Denoise Max mode. $0.08 / run of output image. - [Topaz Restore Image](https://doitong.com/developers/models/topaz/restore/image.md): `topaz/restore/image`. Restores old or damaged photos, either rebuilding detail or removing film dust and scratches. from $0.08 / run of output image. - [Topaz Sharpen Image](https://doitong.com/developers/models/topaz/sharpen/image.md): `topaz/sharpen/image`. Image sharpener with models per blur type, including generative Super Focus for badly blurred shots. $0.08 / run of output image. - [Uno](https://doitong.com/developers/models/uno.md): `uno`. Multi-reference image generation that blends several input images with a text prompt. $0.05 / megapixel. - [Uso](https://doitong.com/developers/models/uso.md): `uso`. Style- and subject-driven image generation from a content image plus one or two style images. $0.10 / megapixel. - Wan 27 (Alibaba), from $0.03: - [Wan · v2.7 · Edit](https://doitong.com/developers/models/wan/v2.7/edit.md): `wan/v2.7/edit`. $0.03 / image. - [Wan · v2.7 · Pro · Edit](https://doitong.com/developers/models/wan/v2.7/pro/edit.md): `wan/v2.7/pro/edit`. $0.075 / image. - [Wan · v2.2 A14b · Image to Image](https://doitong.com/developers/models/wan/v2.2-a14b/image-to-image.md): `wan/v2.2-a14b/image-to-image`. Wan 2.2 A14B image-to-image with adjustable denoising strength to keep or remake the original. $0.05 / image. - [Pixelcut Product Photo](https://doitong.com/developers/models/pixelcut/product-photo.md): `pixelcut/product-photo`. Product image compositor: cuts out the item and places it on a new canvas with background, margins and shadow. $0.024 / image. - [Vidu · Reference to Image](https://doitong.com/developers/models/vidu/reference-to-image.md): `vidu/reference-to-image`. Generates a still image from a prompt and reference images that keep the subject's look. $0.10 / image. - [Ffmpeg Api · Extract Frame](https://doitong.com/developers/models/ffmpeg-api/extract-frame.md): `ffmpeg-api/extract-frame`. Pulls the first, middle or last frame out of a video as an image. $0.0002 / second of input video. - Workflow Utilities (Utility), from $0.001: - [Workflow Utilities Extract Nth Frame](https://doitong.com/developers/models/workflow-utilities/extract-nth-frame.md): `workflow-utilities/extract-nth-frame`. $0.001 / second of processing time (charged by usage, up to $0.90 per run for the example input; the rest is refunded). - [Workflow Utilities Pick Image By Index](https://doitong.com/developers/models/workflow-utilities/pick-image-by-index.md): `workflow-utilities/pick-image-by-index`. $0.001 / run (estimated per run). - [Live Portrait · Image](https://doitong.com/developers/models/live-portrait/image.md): `live-portrait/image`. Edits a single portrait's expression and head pose using sliders, outputting a still image. $0.00125 / second of processing time (charged by usage, up to $1.125 per run for the example input; the rest is refunded). - [Chrono Edit Lora Gallery · Paintbrush](https://doitong.com/developers/models/chrono-edit-lora-gallery/paintbrush.md): `chrono-edit-lora-gallery/paintbrush`. Sketch-guided image edit where painted regions are transformed according to the prompt. from $0.02 / image. - [Google Virtual Try On](https://doitong.com/developers/models/google/virtual-try-on.md): `google/virtual-try-on`. Puts a clothing product onto a person photo, returning 1 to 4 try-on images. $0.075 / image. - [Hi3D Image to Relief](https://doitong.com/developers/models/hitem3d/hi3d/image-to-relief.md): `hitem3d/hi3d/image-to-relief`. Turns one image into a relief depth map as PNG or EXR, with optional background removal. $0.20 / run (estimated per run). - Florence 2 Large (Microsoft), from $0.003: - [Florence-2 Large · Caption to Phrase Grounding](https://doitong.com/developers/models/florence-2-large/caption-to-phrase-grounding.md): `florence-2-large/caption-to-phrase-grounding`. $0.003 / run (estimated per run). - [Florence-2 Large · Dense Region Caption](https://doitong.com/developers/models/florence-2-large/dense-region-caption.md): `florence-2-large/dense-region-caption`. $0.004 / run (estimated per run). - [Florence-2 Large · Object Detection](https://doitong.com/developers/models/florence-2-large/object-detection.md): `florence-2-large/object-detection`. $0.003 / run (estimated per run). - [Florence-2 Large · OCR with Region](https://doitong.com/developers/models/florence-2-large/ocr-with-region.md): `florence-2-large/ocr-with-region`. $0.004 / run (estimated per run). - [Florence-2 Large · Open Vocabulary Detection](https://doitong.com/developers/models/florence-2-large/open-vocabulary-detection.md): `florence-2-large/open-vocabulary-detection`. $0.003 / run (estimated per run). - [Florence-2 Large · Referring Expression Segmentation](https://doitong.com/developers/models/florence-2-large/referring-expression-segmentation.md): `florence-2-large/referring-expression-segmentation`. $0.005 / run (estimated per run). - [Florence-2 Large · Region Proposal](https://doitong.com/developers/models/florence-2-large/region-proposal.md): `florence-2-large/region-proposal`. $0.003 / run (estimated per run). - [Florence-2 Large · Region to Segmentation](https://doitong.com/developers/models/florence-2-large/region-to-segmentation.md): `florence-2-large/region-to-segmentation`. $0.009 / run (estimated per run). - Imageutils (Utility), from $0.002: - [Marigold Depth Estimation](https://doitong.com/developers/models/imageutils/marigold-depth.md): `imageutils/marigold-depth`. $0.014 / run (estimated per run). - [Midas Depth Estimation](https://doitong.com/developers/models/imageutils/depth.md): `imageutils/depth`. $0.002 / run (estimated per run). - [Moondream3 Preview \[Segment\]](https://doitong.com/developers/models/moondream3-preview/segment.md): `moondream3-preview/segment`. Segments a named object in an image, returning a mask, bounding box and SVG path. $0.003 / run (estimated per run). - [MoonDreamNext Detection](https://doitong.com/developers/models/moondream-next/detection.md): `moondream-next/detection`. Runs bounding-box, point or gaze detection on an image and draws the result. $0.002 / run (estimated per run). ## Models: Text to Video (126) - [Wan v2.6 Text to Video](https://doitong.com/developers/models/wan/v2.6/text-to-video.md): `wan/v2.6/text-to-video`. Wan 2.6 text-to-video with 5, 10 or 15 second clips, five aspect ratios and optional background audio. from $0.10 / second (5 s ≈ $0.50). - [Vidu · Q2 · Text to Video](https://doitong.com/developers/models/vidu/q2/text-to-video.md): `vidu/q2/text-to-video`. Q2 text-to-video with 2-8 second clips and resolutions from 360p to 1080p. from $0.10 / run. - [Wan 2.5 Text to Video](https://doitong.com/developers/models/wan-25-preview/text-to-video.md): `wan-25-preview/text-to-video`. Wan 2.5 text-to-video with 480p to 1080p output, 5 or 10 seconds, and optional audio track. from $0.05 / second (5 s ≈ $0.25). - Wan v22 (Alibaba), from $0.08: - [Wan v2.2 5B · Text to Video](https://doitong.com/developers/models/wan/v2.2-5b/text-to-video.md): `wan/v2.2-5b/text-to-video`. $0.15 / video. - [Wan · v2.2 5b · Text to Video · Distill](https://doitong.com/developers/models/wan/v2.2-5b/text-to-video/distill.md): `wan/v2.2-5b/text-to-video/distill`. $0.08 / video. - [Wan-2.2 Text-to-Video A14B](https://doitong.com/developers/models/wan/v2.2-a14b/text-to-video.md): `wan/v2.2-a14b/text-to-video`. A14B text-to-video with 480p to 720p output, two guidance stages and optional interpolation. from $0.04 / second of output video. - [Wan-2.2 Text-to-Video A14B with LoRAs](https://doitong.com/developers/models/wan/v2.2-a14b/text-to-video/lora.md): `wan/v2.2-a14b/text-to-video/lora`. A14B text-to-video with LoRA support and optional reversed playback. from $0.507 / run (estimated per run). - [Bernini-R Text to Video](https://doitong.com/developers/models/bernini-r/text-to-video.md): `bernini-r/text-to-video`. Generates a video from a text prompt alone, with 16:9, 9:16 or 1:1 output. from $0.04 / second of output video. - [FLUX 3 Max Text to Video](https://doitong.com/developers/models/blackforestlabs/flux-3-max/text-to-video.md): `blackforestlabs/flux-3-max/text-to-video`. Black Forest Labs' video model, 5 to 20 second clips with sound at 720p or 1080p. from $0.0425 / second of output video. - Grok Imagine (xAI), from $0.30: - [Grok Imagine Video 1.5 Text to Video](https://doitong.com/developers/models/xai/grok-imagine-video/v1.5/text-to-video.md): `xai/grok-imagine-video/v1.5/text-to-video`. from $0.08 / second (6 s ≈ $0.48). - [Grok Imagine Video · Text to Video](https://doitong.com/developers/models/xai/grok-imagine-video/text-to-video.md): `xai/grok-imagine-video/text-to-video`. from $0.05 / second (6 s ≈ $0.30). - Kling v3 (Kling), from $0.42: - [Kling 3.0 Pro Text to Video](https://doitong.com/developers/models/kling-video/v3/pro/text-to-video.md): `kling-video/v3/pro/text-to-video`. from $0.112 / second (5 s ≈ $0.56). - [Kling Video V3 Text to Video 4K](https://doitong.com/developers/models/kling-video/v3/4k/text-to-video.md): `kling-video/v3/4k/text-to-video`. $0.42 / second (5 s ≈ $2.10). - [Kling Video v3 Text to Video \[Standard\]](https://doitong.com/developers/models/kling-video/v3/standard/text-to-video.md): `kling-video/v3/standard/text-to-video`. from $0.084 / second (5 s ≈ $0.42). - LTX 2.5 (Lightricks), from $0.54: - [LTX 2.5 Pro Text to Video](https://doitong.com/developers/models/lightricks/ltx-2.5/text-to-video/pro.md): `lightricks/ltx-2.5/text-to-video/pro`. from $0.12 / second (6 s ≈ $0.72). - [Ltx 2.5 Text to Video Fast](https://doitong.com/developers/models/lightricks/ltx-2.5/text-to-video/fast.md): `lightricks/ltx-2.5/text-to-video/fast`. from $0.09 / second (6 s ≈ $0.54). - [MiniMax H3 Text to Video](https://doitong.com/developers/models/minimax/h3/text-to-video.md): `minimax/h3/text-to-video`. MiniMax's (Hailuo) video model for lively motion, 5 to 15 seconds, up to 4K. from $0.05 / second (5 s ≈ $0.25). - Seedance 2.0 (ByteDance), from $0.289: - [Seedance 2.0 Fast Text to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/fast/text-to-video.md): `bytedance/seedance-2.0/fast/text-to-video`. from $0.113 / second (4 s ≈ $0.452). - [Seedance 2.0 Mini Text to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/mini/text-to-video.md): `bytedance/seedance-2.0/mini/text-to-video`. from $0.0721 / second (4 s ≈ $0.289). - [Seedance 2.0 Text to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/text-to-video.md): `bytedance/seedance-2.0/text-to-video`. from $0.141 / second (4 s ≈ $0.564). - Veo 3.1 (Google), from $0.80: - [Veo 3.1](https://doitong.com/developers/models/veo3.1.md): `veo3.1`. from $0.20 / second (8 s ≈ $1.60). - [Veo 3.1 Fast](https://doitong.com/developers/models/veo3.1/fast.md): `veo3.1/fast`. from $0.10 / second (8 s ≈ $0.80). - [Wan 3.0 Text to Video](https://doitong.com/developers/models/alibaba/wan-3.0/text-to-video.md): `alibaba/wan-3.0/text-to-video`. Alibaba's Wan 3.0, clips of 2 to 30 seconds with generated audio at up to 1080p. from $0.05 / second (5 s ≈ $0.25). - [AnimateDiff Turbo · Text to Video](https://doitong.com/developers/models/fast-animatediff/turbo/text-to-video.md): `fast-animatediff/turbo/text-to-video`. Fast AnimateDiff Turbo text-to-video, tuned for 4 to 12 steps and low guidance. from $0.014 / run (estimated per run). - [Bytedance Seedance V1.5 Pro Text To Video](https://doitong.com/developers/models/bytedance/seedance/v1.5/pro/text-to-video.md): `bytedance/seedance/v1.5/pro/text-to-video`. Seedance 1.5 Pro text-to-video that also generates audio, 4 to 12 seconds. from $0.0117 / second of output video. - [CogVideoX-5B](https://doitong.com/developers/models/cogvideox-5b.md): `cogvideox-5b`. Text-to-video generation with CogVideoX-5B, with LoRA support and adjustable frame rate. $0.20 / video. - Cosmos Predict 2.5 2B (NVIDIA), from $0.08: - [Cosmos Predict 2.5 2B Distilled](https://doitong.com/developers/models/cosmos-predict-2.5/distilled/text-to-video.md): `cosmos-predict-2.5/distilled/text-to-video`. $0.08 / video. - [Cosmos Predict 2.5 2B · Text to Video](https://doitong.com/developers/models/cosmos-predict-2.5/text-to-video.md): `cosmos-predict-2.5/text-to-video`. $0.20 / video. - [Boreal](https://doitong.com/developers/models/creatify/boreal.md): `creatify/boreal`. Text-to-video with native synchronized audio for product, UGC and presenter clips, optional image and audio. from $0.01 / second of output video. - [AnimateDiff · Text to Video](https://doitong.com/developers/models/fast-animatediff/text-to-video.md): `fast-animatediff/text-to-video`. AnimateDiff text-to-video with 1 to 32 frames and optional motion presets. from $0.023 / run (estimated per run). - [Gemini Omni Flash](https://doitong.com/developers/models/google/gemini-omni-flash.md): `google/gemini-omni-flash`. Original-version text-to-video with synchronized audio, 3 to 10 second clips in 16:9 or 9:16. from $1.271 / run (estimated per run). - [Grok Imagine Video 1.5 Lite Text to Video](https://doitong.com/developers/models/xai/grok-imagine-video/v1.5/lite/text-to-video.md): `xai/grok-imagine-video/v1.5/lite/text-to-video`. Lite 1.5 text-to-video with 1 to 15 second clips and resolutions up to 1080p. from $0.02 / second of output video. - H3 Max (MiniMax), from $0.40: - [H3 Max 16-bit Pixel](https://doitong.com/developers/models/minimax/h3-max/styles/16bit-pixel.md): `minimax/h3-max/styles/16bit-pixel`. $0.08 / second (5 s ≈ $0.40). - [H3 Max Hand Drawn](https://doitong.com/developers/models/minimax/h3-max/styles/hand-drawn.md): `minimax/h3-max/styles/hand-drawn`. $0.08 / second (5 s ≈ $0.40). - [H3 Max Low Poly](https://doitong.com/developers/models/minimax/h3-max/styles/low-poly.md): `minimax/h3-max/styles/low-poly`. $0.08 / second (5 s ≈ $0.40). - [H3 Max Retro Toon 70s](https://doitong.com/developers/models/minimax/h3-max/styles/retro-toon-70s.md): `minimax/h3-max/styles/retro-toon-70s`. $0.08 / second (5 s ≈ $0.40). - [H3 Max VHS](https://doitong.com/developers/models/minimax/h3-max/styles/vhs.md): `minimax/h3-max/styles/vhs`. $0.08 / second (5 s ≈ $0.40). - Hailuo 02 (MiniMax), from $0.27: - [MiniMax Hailuo 02 \[Pro\] (Text to Video)](https://doitong.com/developers/models/minimax/hailuo-02/pro/text-to-video.md): `minimax/hailuo-02/pro/text-to-video`. $0.48 / run (estimated per run). - [MiniMax Hailuo 02 \[Standard\] (Text to Video)](https://doitong.com/developers/models/minimax/hailuo-02/standard/text-to-video.md): `minimax/hailuo-02/standard/text-to-video`. $0.045 / second (6 s ≈ $0.27). - [Happy Horse 1.1 Text to Video](https://doitong.com/developers/models/alibaba/happy-horse/v1.1/text-to-video.md): `alibaba/happy-horse/v1.1/text-to-video`. Prompt-only video generation with 3-15 second clips, 720p or 1080p, and nine aspect ratios. from $0.14 / second (5 s ≈ $0.70). - [Heygen · v2 · Video Agent](https://doitong.com/developers/models/heygen/v2/video-agent.md): `heygen/v2/video-agent`. Text-to-video agent that builds a full video from a natural-language prompt and a config object. $0.937 / run (estimated per run). - [Heygen Video Agent](https://doitong.com/developers/models/heygen/v3/video-agent.md): `heygen/v3/video-agent`. Agent that makes a video from one prompt, picking avatar, voice and script, with up to 20 asset files. $3.706 / run (estimated per run). - [Hunyuan Video](https://doitong.com/developers/models/hunyuan-video.md): `hunyuan-video`. Text-to-video generation with 480p, 580p or 720p output and a higher-step pro mode. $0.40 / video. - [Hunyuan Video V1.5 · Text to Video](https://doitong.com/developers/models/hunyuan-video-v1.5/text-to-video.md): `hunyuan-video-v1.5/text-to-video`. Version 1.5 text-to-video with negative prompt, prompt expansion and up to 121 frames. $0.075 / run (estimated per run). - [Infinity Star](https://doitong.com/developers/models/infinity-star/text-to-video.md): `infinity-star/text-to-video`. Autoregressive text-to-video with 16:9, 1:1 or 9:16 output, negative prompt, and optional prompt enhancement. $0.07 / video. - [Kandinsky 6.0 Lite · Text to Video](https://doitong.com/developers/models/kandinsky6-lite/text-to-video.md): `kandinsky6-lite/text-to-video`. Lightweight text-to-video with optional synced audio, five aspect ratios and an optional super-resolution pass. from $0.08 / run. - [Kandinsky 6.0 Pro · Text to Video](https://doitong.com/developers/models/kandinsky6-pro/text-to-video.md): `kandinsky6-pro/text-to-video`. Pro text-to-video with negative prompt, guidance scale, up to 50 steps, optional audio and upscaling. from $0.244 / run. - Kandinsky5 (Sber AI), from $0.05: - [Kandinsky5](https://doitong.com/developers/models/kandinsky5/text-to-video.md): `kandinsky5/text-to-video`. from $0.08 / video. - [Kandinsky5 · Distill](https://doitong.com/developers/models/kandinsky5/text-to-video/distill.md): `kandinsky5/text-to-video/distill`. from $0.05 / video. - [Kandinsky5 Pro · Text to Video](https://doitong.com/developers/models/kandinsky5-pro/text-to-video.md): `kandinsky5-pro/text-to-video`. Kandinsky 5 Pro text-to-video at 512P or 1024P with 3:2, 1:1, or 2:3 aspect ratios. from $0.20 / video. - [Kling 4.0 Text to Video](https://doitong.com/developers/models/kling/v4/text-to-video.md): `kling/v4/text-to-video`. Text-only video generation with optional per-shot prompts, 3 to 30 second clips at 720p or 1080p. from $0.157 / second of output video. - Kling O3 (Kling), from $0.42: - [Kling O3 Text to Video \[Pro\]](https://doitong.com/developers/models/kling-video/o3/pro/text-to-video.md): `kling-video/o3/pro/text-to-video`. from $0.112 / second (5 s ≈ $0.56). - [Kling O3 Text to Video \[Standard\]](https://doitong.com/developers/models/kling-video/o3/standard/text-to-video.md): `kling-video/o3/standard/text-to-video`. from $0.084 / second (5 s ≈ $0.42). - [Kling Video · O3 · 4k · Text to Video](https://doitong.com/developers/models/kling-video/o3/4k/text-to-video.md): `kling-video/o3/4k/text-to-video`. $0.42 / second (5 s ≈ $2.10). - Kling Video Effects (Kling), from $0.225: - [Kling 1.0](https://doitong.com/developers/models/kling-video/v1/standard/effects.md): `kling-video/v1/standard/effects`. $0.045 / second (5 s ≈ $0.225). - [Kling 1.5](https://doitong.com/developers/models/kling-video/v1.5/pro/effects.md): `kling-video/v1.5/pro/effects`. $0.10 / second (5 s ≈ $0.50). - [Kling 1.6 · Pro · Effects](https://doitong.com/developers/models/kling-video/v1.6/pro/effects.md): `kling-video/v1.6/pro/effects`. $0.098 / second (5 s ≈ $0.49). - [Kling 1.6 · Standard · Effects](https://doitong.com/developers/models/kling-video/v1.6/standard/effects.md): `kling-video/v1.6/standard/effects`. $0.056 / second (5 s ≈ $0.28). - [Kling Video v2.6 Text to Video](https://doitong.com/developers/models/kling-video/v2.6/pro/text-to-video.md): `kling-video/v2.6/pro/text-to-video`. v2.6 text-to-video with native audio output, 5 or 10 s clips, and CFG and aspect ratio control. from $0.07 / second (5 s ≈ $0.35). - [Kling v2.5 Text to Video](https://doitong.com/developers/models/kling-video/v2.5-turbo/pro/text-to-video.md): `kling-video/v2.5-turbo/pro/text-to-video`. v2.5 Turbo Pro text-to-video with aspect ratio and CFG control, 5 or 10 s clips. $0.07 / second (5 s ≈ $0.35). - Kling Video V3 (Kling), from $0.56: - [Kling Video V3 Standard Turbo Text to Video](https://doitong.com/developers/models/kling-video/v3/turbo/standard/text-to-video.md): `kling-video/v3/turbo/standard/text-to-video`. $0.112 / second (5 s ≈ $0.56). - [Kling Video V3 Turbo Pro Text to Video](https://doitong.com/developers/models/kling-video/v3/turbo/pro/text-to-video.md): `kling-video/v3/turbo/pro/text-to-video`. $0.14 / second (5 s ≈ $0.70). - [Krea Wan 14b- Text to Video](https://doitong.com/developers/models/krea-wan-14b/text-to-video.md): `krea-wan-14b/text-to-video`. Krea Wan 14b text-to-video with frame-count control from 18 to 162 frames. $0.025 / second of output video. - LongCat Video (Meituan), from $0.025: - [LongCat Video · Text to Video · 480p](https://doitong.com/developers/models/longcat-video/text-to-video/480p.md): `longcat-video/text-to-video/480p`. $0.025 / second of output video. - [LongCat Video · Text to Video · 720p](https://doitong.com/developers/models/longcat-video/text-to-video/720p.md): `longcat-video/text-to-video/720p`. $0.04 / second of output video. - LongCat Video Distilled (Meituan), from $0.005: - [LongCat Video Distilled · Text to Video · 480p](https://doitong.com/developers/models/longcat-video/distilled/text-to-video/480p.md): `longcat-video/distilled/text-to-video/480p`. $0.005 / second of output video. - [LongCat Video Distilled · Text to Video · 720p](https://doitong.com/developers/models/longcat-video/distilled/text-to-video/720p.md): `longcat-video/distilled/text-to-video/720p`. $0.01 / second of output video. - [LTX Video (preview)](https://doitong.com/developers/models/ltx-video.md): `ltx-video`. Early preview text-to-video model that makes clips from a prompt alone. $0.02 / video. - [LTX Video-0.9.5](https://doitong.com/developers/models/ltx-video-v095.md): `ltx-video-v095`. LTX Video 0.9.5 text-to-video at 480p or 720p in 16:9 or 9:16, with prompt expansion. $0.04 / video. - [LTX Video-0.9.7 13B Distilled](https://doitong.com/developers/models/ltx-video-13b-distilled.md): `ltx-video-13b-distilled`. Text-to-video with the older 0.9.7 distilled 13B model, supporting LoRAs and long frame counts. from $0.04 / second of output video. - LTX-2.3 22B Distilled (Lightricks), from $0.002: - [LTX-2.3 22B Distilled · Text to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/text-to-video.md): `ltx-2.3-22b/distilled/text-to-video`. $0.00121 / megapixel of output video. - [LTX-2.3 22B Distilled · Text to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/distilled/text-to-video/lora.md): `ltx-2.3-22b/distilled/text-to-video/lora`. $0.00141 / megapixel of output video. - [LTX-Video 13B 0.9.8 Distilled](https://doitong.com/developers/models/ltxv-13b-098-distilled.md): `ltxv-13b-098-distilled`. Text-to-video with the 0.9.8 distilled 13B model, supporting LoRAs and clips up to 1441 frames. from $0.02 / second of output video. - [MAGI-1 (Distilled)](https://doitong.com/developers/models/magi-distilled.md): `magi-distilled`. Distilled MAGI-1 text-to-video with 480p or 720p output and selectable step counts of 4 to 32. from $0.08 / second of output video. - MiniMax (Hailuo AI) Video 01 (MiniMax), from $0.50: - [MiniMax (Hailuo AI) Video 01](https://doitong.com/developers/models/minimax/video-01.md): `minimax/video-01`. $0.50 / video. - [MiniMax (Hailuo AI) Video 01 Director](https://doitong.com/developers/models/minimax/video-01-director.md): `minimax/video-01-director`. $0.50 / video. - [MiniMax (Hailuo AI) Video 01 Live](https://doitong.com/developers/models/minimax/video-01-live.md): `minimax/video-01-live`. $0.50 / video. - [MiniMax H3 Text to Video LoRA](https://doitong.com/developers/models/minimax/h3/text-to-video/lora.md): `minimax/h3/text-to-video/lora`. Text-to-video with 1 to 3 trained LoRA adapters applied, offering six aspect ratios and 5 to 15 second clips. from $0.0625 / second (5 s ≈ $0.313). - MiniMax Hailuo 2.3 (MiniMax), from $0.28: - [MiniMax Hailuo 2.3 \[Pro\] (Text to Video)](https://doitong.com/developers/models/minimax/hailuo-2.3/pro/text-to-video.md): `minimax/hailuo-2.3/pro/text-to-video`. $0.49 / run (estimated per run). - [MiniMax Hailuo 2.3 \[Standard\] (Text to Video)](https://doitong.com/developers/models/minimax/hailuo-2.3/standard/text-to-video.md): `minimax/hailuo-2.3/standard/text-to-video`. from $0.28 / run (estimated per run). - [Ovi Text to Video](https://doitong.com/developers/models/ovi.md): `ovi`. Text-to-video model that generates video together with its audio track. $0.20 / video. - [Seedance 2.0 US Text to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/us/text-to-video.md): `bytedance/seedance-2.0/us/text-to-video`. Seedance 2.0 text-to-video with resolutions up to 4k and 4 to 15 second clips. from $0.1731 / second (4 s ≈ $0.693). - [Seedance 2.5 US Text to Video](https://doitong.com/developers/models/bytedance/seedance-2.5/us/text-to-video.md): `bytedance/seedance-2.5/us/text-to-video`. Seedance 2.5 text-to-video with clips up to 30 seconds and output up to 1080p. $0.0107 / 1000 tokens (charged by usage, up to $6.944 per run for the example input; the rest is refunded). - Seedance v1 (ByteDance), from $0.01: - [Bytedance Seedance V1 Pro Fast Text To Video](https://doitong.com/developers/models/bytedance/seedance/v1/pro/fast/text-to-video.md): `bytedance/seedance/v1/pro/fast/text-to-video`. from $0.00972 / second of output video. - [Seedance 1.0 Pro · Text to Video](https://doitong.com/developers/models/bytedance/seedance/v1/pro/text-to-video.md): `bytedance/seedance/v1/pro/text-to-video`. from $0.0243 / second of output video. - [Stable Video Diffusion](https://doitong.com/developers/models/fast-svd/text-to-video.md): `fast-svd/text-to-video`. Text-to-video with SVD v1.1 that gives control over motion strength, fps, step count and noise augmentation. $0.033 / run (estimated per run). - [T2V Turbo - Video Crafter](https://doitong.com/developers/models/t2v-turbo.md): `t2v-turbo`. Quick text-to-video from a prompt, 16 to 32 frames with adjustable export fps. from $0.024 / run (estimated per run). - [Vidu Text to Video](https://doitong.com/developers/models/vidu/q1/text-to-video.md): `vidu/q1/text-to-video`. Q1 text-to-video with a general or anime style option and 16:9, 9:16 or 1:1 output. $0.40 / run (estimated per run). - Vidu Q3 (Vidu), from $0.175: - [Vidu · Q3 · Text to Video](https://doitong.com/developers/models/vidu/q3/text-to-video.md): `vidu/q3/text-to-video`. from $0.07 / second (5 s ≈ $0.35). - [Vidu · Q3 · Text to Video · Turbo](https://doitong.com/developers/models/vidu/q3/text-to-video/turbo.md): `vidu/q3/text-to-video/turbo`. from $0.035 / second (5 s ≈ $0.175). - [Wan 3.0 Prime · Text to Video](https://doitong.com/developers/models/alibaba/wan-3.0-prime/text-to-video.md): `alibaba/wan-3.0-prime/text-to-video`. Text-to-video with clips of 2-30 seconds, optional audio and an adaptive aspect ratio. from $0.068 / second (5 s ≈ $0.34). - [Wan · v2.2 5b · Text to Video · Fast Wan](https://doitong.com/developers/models/wan/v2.2-5b/text-to-video/fast-wan.md): `wan/v2.2-5b/text-to-video/fast-wan`. Fast Wan 5B text-to-video with 480p, 580p or 720p output and optional interpolation. from $0.0125 / video. - [Wan · v2.2 A14b · Text to Video · Turbo](https://doitong.com/developers/models/wan/v2.2-a14b/text-to-video/turbo.md): `wan/v2.2-a14b/text-to-video/turbo`. Turbo A14B text-to-video with minimal controls: prompt, resolution and aspect ratio. from $0.05 / video. - [Wan-2.1 Text-to-Video with LoRAs](https://doitong.com/developers/models/wan-t2v-lora.md): `wan-t2v-lora`. Wan 2.1 text-to-video that accepts custom LoRA weights, with turbo mode and optional reversal. $0.75 / video. - [Marey Realism V1.5 · T2V](https://doitong.com/developers/models/moonvalley/marey/t2v.md): `moonvalley/marey/t2v`. Marey text-to-video with 5s or 10s clips in 1080p-class landscape or square-ish sizes. $0.30 / second (5 s ≈ $1.50). - Pika (Pika), from $0.20: - [Pika Text to Video (v2.1)](https://doitong.com/developers/models/pika/v2.1/text-to-video.md): `pika/v2.1/text-to-video`. $0.40 / video. - [Pika Text to Video (v2.2)](https://doitong.com/developers/models/pika/v2.2/text-to-video.md): `pika/v2.2/text-to-video`. from $0.20 / video. - [Pika Text to Video Turbo (v2)](https://doitong.com/developers/models/pika/v2/turbo/text-to-video.md): `pika/v2/turbo/text-to-video`. $0.20 / video. - PixVerse (PixVerse), from $0.15: - [PixVerse V3.5 Text To Video](https://doitong.com/developers/models/pixverse/v3.5/text-to-video.md): `pixverse/v3.5/text-to-video`. from $0.15 / run. - [PixVerse V3.5 Text To Video Fast](https://doitong.com/developers/models/pixverse/v3.5/text-to-video/fast.md): `pixverse/v3.5/text-to-video/fast`. from $0.30 / request. - [PixVerse V4 Text To Video](https://doitong.com/developers/models/pixverse/v4/text-to-video.md): `pixverse/v4/text-to-video`. from $0.15 / run. - [PixVerse V4 Text To Video Fast](https://doitong.com/developers/models/pixverse/v4/text-to-video/fast.md): `pixverse/v4/text-to-video/fast`. from $0.30 / request. - [PixVerse C1 Text To Video](https://doitong.com/developers/models/pixverse/c1/text-to-video.md): `pixverse/c1/text-to-video`. C1 text-to-video with 1 to 15 second clips, eight aspect ratios, up to 1080p and optional audio. from $0.03 / second (5 s ≈ $0.15). - [PixVerse V5 Text To Video](https://doitong.com/developers/models/pixverse/v5/text-to-video.md): `pixverse/v5/text-to-video`. PixVerse V5 text-to-video with aspect ratio, resolution and style controls. from $0.15 / run. - [PixVerse V5.5 Text To Video](https://doitong.com/developers/models/pixverse/v5.5/text-to-video.md): `pixverse/v5.5/text-to-video`. PixVerse V5.5 text-to-video with optional audio, multi-clip shots and 10 second duration. from $0.15 / run. - [PixVerse V5.6 Text To Video](https://doitong.com/developers/models/pixverse/v5.6/text-to-video.md): `pixverse/v5.6/text-to-video`. Creates a 5, 8 or 10 second video from text alone, with five aspect ratios and optional style presets. from $0.35 / run. - [Stable Video Diffusion Turbo · Text to Video](https://doitong.com/developers/models/fast-svd-lcm/text-to-video.md): `fast-svd-lcm/text-to-video`. Turbo Stable Video Diffusion variant that creates a short video from a text prompt only. $0.028 / run (estimated per run). - Wan 2.1 (Alibaba), from $0.20: - [Wan-2.1 Pro Text-to-Video](https://doitong.com/developers/models/wan-pro/text-to-video.md): `wan-pro/text-to-video`. $0.80 / run (estimated per run). - [Wan-2.1 Text-to-Video](https://doitong.com/developers/models/wan-t2v.md): `wan-t2v`. from $0.20 / video. - [Flux 3 Text To Video Draft](https://doitong.com/developers/models/blackforestlabs/flux-3/text-to-video/draft.md): `blackforestlabs/flux-3/text-to-video/draft`. Draft video generated from a text prompt only, with optional audio. $0.06 / second (5 s ≈ $0.30). - [Gemini Omni Flash 1.1 Text to Video](https://doitong.com/developers/models/google/gemini-omni-flash/v1.1/text-to-video.md): `google/gemini-omni-flash/v1.1/text-to-video`. Version 1.1 text-only video generation with native audio, selectable resolution from 360p up to 4k. from $0.03 / second (8 s ≈ $0.24). - [H3 Max Turbo Text to Video](https://doitong.com/developers/models/minimax/h3-max-turbo/text-to-video.md): `minimax/h3-max-turbo/text-to-video`. Turbo variant that generates video from a text prompt only, with six aspect ratios and optional audio track. from $0.0163 / second of output video. - [MiniMax H3 Max Text to Video](https://doitong.com/developers/models/minimax/h3-max/text-to-video.md): `minimax/h3-max/text-to-video`. Standard H3 Max text-to-video with six aspect ratios, up to 1080P, and an optional audio track. from $0.0325 / second of output video. - [Happy Horse · Text to Video](https://doitong.com/developers/models/alibaba/happy-horse/text-to-video.md): `alibaba/happy-horse/text-to-video`. Text-only video generation with 3 to 15 second clips at 720p or 1080p in five aspect ratios. from $0.14 / second (5 s ≈ $0.70). - LTX 2.3 (Lightricks), from $0.36: - [LTX 2.3 Video Fast · Text to Video](https://doitong.com/developers/models/ltx-2.3/text-to-video/fast.md): `ltx-2.3/text-to-video/fast`. from $0.06 / second (6 s ≈ $0.36). - [LTX Video 2.3 Pro · Text to Video](https://doitong.com/developers/models/ltx-2.3/text-to-video.md): `ltx-2.3/text-to-video`. from $0.08 / second (6 s ≈ $0.48). - LTX 2.3 22b (Lightricks), from $0.002: - [LTX-2.3 22B · Text to Video](https://doitong.com/developers/models/ltx-2.3-22b/text-to-video.md): `ltx-2.3-22b/text-to-video`. $0.00161 / megapixel of output video. - [LTX-2.3 22B · Text to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/text-to-video/lora.md): `ltx-2.3-22b/text-to-video/lora`. $0.00181 / megapixel of output video. - LTX 2.3 Quality (Lightricks), from $0.003: - [Ltx 2.3 Quality · Text to Video](https://doitong.com/developers/models/ltx-2.3-quality/text-to-video.md): `ltx-2.3-quality/text-to-video`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Text to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/text-to-video/lora.md): `ltx-2.3-quality/text-to-video/lora`. $0.00271 / megapixel of output video. - [Luma Ray 3.2 Text to Video](https://doitong.com/developers/models/luma/agent/ray/v3.2/text-to-video.md): `luma/agent/ray/v3.2/text-to-video`. Ray 3.2 text-to-video with 5s or 10s clips, six aspect ratios, looping and optional HDR with EXR export. from $0.10 / second (5 s ≈ $0.50). - PixVerse 45 (PixVerse), from $0.15: - [PixVerse V4.5 Text To Video](https://doitong.com/developers/models/pixverse/v4.5/text-to-video.md): `pixverse/v4.5/text-to-video`. from $0.15 / run. - [PixVerse V4.5 Text To Video Fast](https://doitong.com/developers/models/pixverse/v4.5/text-to-video/fast.md): `pixverse/v4.5/text-to-video/fast`. from $0.30 / request. - [PixVerse V6 Text To Video](https://doitong.com/developers/models/pixverse/v6/text-to-video.md): `pixverse/v6/text-to-video`. Text-to-video with 1 to 15 second durations, eight aspect ratios including 21:9, and multi-clip option. from $0.025 / second (5 s ≈ $0.125). - [Wan Text to Video](https://doitong.com/developers/models/wan/v2.7/text-to-video.md): `wan/v2.7/text-to-video`. Text-to-video with 2-15 second clips, five aspect ratios and optional driving audio. from $0.10 / second (5 s ≈ $0.50). - [Flux 3 Text to Video](https://doitong.com/developers/models/blackforestlabs/flux-3/text-to-video.md): `blackforestlabs/flux-3/text-to-video`. Text-to-video at full quality, with optional audio and output up to 2160p. from $0.17 / second (5 s ≈ $0.85). ## Models: Image to Video (152) - [Wan v2.6 Image to Video](https://doitong.com/developers/models/wan/v2.6/image-to-video.md): `wan/v2.6/image-to-video`. Animates a first-frame image into a 5, 10 or 15 second clip at 720p or 1080p, with optional audio. from $0.10 / second (5 s ≈ $0.50). - [Cosmos 3 Super Image to Video](https://doitong.com/developers/models/nvidia/cosmos-3-super/image-to-video.md): `nvidia/cosmos-3-super/image-to-video`. Animates a first-frame image into a video, with optional prompt expansion and an agentic refinement loop. from $0.05 / second of output video. - Vidu Q2 (Vidu), from $0.10: - [Vidu · Q2 · Image to Video · Pro](https://doitong.com/developers/models/vidu/q2/image-to-video/pro.md): `vidu/q2/image-to-video/pro`. from $0.20 / run. - [Vidu · Q2 · Image to Video · Turbo](https://doitong.com/developers/models/vidu/q2/image-to-video/turbo.md): `vidu/q2/image-to-video/turbo`. from $0.10 / run. - [Wan 2.5 Image to Video](https://doitong.com/developers/models/wan-25-preview/image-to-video.md): `wan-25-preview/image-to-video`. Wan 2.5 image-to-video at 480p to 1080p, 5 or 10 seconds, with optional background audio. from $0.05 / second (5 s ≈ $0.25). - [Wan v2.2 5B · Image to Video](https://doitong.com/developers/models/wan/v2.2-5b/image-to-video.md): `wan/v2.2-5b/image-to-video`. Wan 2.2 5B image-to-video with flexible frame counts, 580p or 720p, and frame interpolation. $0.15 / video. - [Wan v2.2 A14B](https://doitong.com/developers/models/wan/v2.2-a14b/image-to-video.md): `wan/v2.2-a14b/image-to-video`. Animates one still image into a clip, with optional end frame, frame interpolation and detailed sampling controls. from $0.04 / second of output video. - [Wan v2.2 A14B Image-to-Video A14B with LoRAs](https://doitong.com/developers/models/wan/v2.2-a14b/image-to-video/lora.md): `wan/v2.2-a14b/image-to-video/lora`. A14B image-to-video that accepts Wan 2.2 LoRA weights and can reverse the clip. from $1.006 / run (estimated per run). - FLUX 3 Max (Black Forest Labs), from $0.043: - [FLUX 3 Max Image to Video](https://doitong.com/developers/models/blackforestlabs/flux-3-max/image-to-video.md): `blackforestlabs/flux-3-max/image-to-video`. from $0.0425 / second of output video. - [FLUX 3 Max Keyframes to Video](https://doitong.com/developers/models/blackforestlabs/flux-3-max/keyframes-to-video.md): `blackforestlabs/flux-3-max/keyframes-to-video`. from $0.0425 / second (5 s ≈ $0.213). - Grok Imagine (xAI), from $0.05: - [Grok Imagine Video 1.5 Image to Video](https://doitong.com/developers/models/xai/grok-imagine-video/v1.5/image-to-video.md): `xai/grok-imagine-video/v1.5/image-to-video`. from $0.082 / second (6 s ≈ $0.492). - [Grok Imagine Video · Image to Video](https://doitong.com/developers/models/xai/grok-imagine-video/image-to-video.md): `xai/grok-imagine-video/image-to-video`. from $0.05 / second of output video. - Kling v3 (Kling), from $0.42: - [Kling 3.0 Pro Image to Video](https://doitong.com/developers/models/kling-video/v3/pro/image-to-video.md): `kling-video/v3/pro/image-to-video`. from $0.112 / second (5 s ≈ $0.56). - [Kling Video v3 Image to Video \[Standard\]](https://doitong.com/developers/models/kling-video/v3/standard/image-to-video.md): `kling-video/v3/standard/image-to-video`. from $0.084 / second (5 s ≈ $0.42). - [Kling Video · v3 · 4k · Image to Video](https://doitong.com/developers/models/kling-video/v3/4k/image-to-video.md): `kling-video/v3/4k/image-to-video`. $0.42 / second (5 s ≈ $2.10). - LTX 2.5 (Lightricks), from $0.54: - [LTX 2.5 Image to Video Fast](https://doitong.com/developers/models/lightricks/ltx-2.5/image-to-video/fast.md): `lightricks/ltx-2.5/image-to-video/fast`. from $0.09 / second (6 s ≈ $0.54). - [LTX 2.5 Pro Image to Video](https://doitong.com/developers/models/lightricks/ltx-2.5/image-to-video/pro.md): `lightricks/ltx-2.5/image-to-video/pro`. from $0.12 / second (6 s ≈ $0.72). - [MiniMax H3 Image to Video](https://doitong.com/developers/models/minimax/h3/image-to-video.md): `minimax/h3/image-to-video`. Animates a first frame, a last frame or both into a 5 to 15 second MiniMax H3 clip, up to 4K. from $0.05 / second (5 s ≈ $0.25). - Seedance 2.0 (ByteDance), from $0.289: - [Seedance 2.0 Fast Image to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/fast/image-to-video.md): `bytedance/seedance-2.0/fast/image-to-video`. from $0.113 / second (4 s ≈ $0.452). - [Seedance 2.0 Image to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/image-to-video.md): `bytedance/seedance-2.0/image-to-video`. from $0.141 / second (4 s ≈ $0.564). - [Seedance 2.0 Mini Image to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/mini/image-to-video.md): `bytedance/seedance-2.0/mini/image-to-video`. from $0.0721 / second (4 s ≈ $0.289). - Veo 3.1 (Google), from $0.80: - [Veo 3.1 Fast Image to Video](https://doitong.com/developers/models/veo3.1/fast/image-to-video.md): `veo3.1/fast/image-to-video`. from $0.10 / second (8 s ≈ $0.80). - [Veo 3.1 Image to Video](https://doitong.com/developers/models/veo3.1/image-to-video.md): `veo3.1/image-to-video`. from $0.20 / second (8 s ≈ $1.60). - [Veo3.1 Fast First Last Frame to Video](https://doitong.com/developers/models/veo3.1/fast/first-last-frame-to-video.md): `veo3.1/fast/first-last-frame-to-video`. from $0.10 / second (8 s ≈ $0.80). - [Veo3.1 First Last Frame to Video](https://doitong.com/developers/models/veo3.1/first-last-frame-to-video.md): `veo3.1/first-last-frame-to-video`. from $0.20 / second (8 s ≈ $1.60). - [Wan 3.0 Image to Video](https://doitong.com/developers/models/alibaba/wan-3.0/image-to-video.md): `alibaba/wan-3.0/image-to-video`. Animates a first frame, optionally toward a last frame, into a 2 to 30 second Wan 3.0 clip with audio. from $0.05 / second (5 s ≈ $0.25). - [Bytedance Seedance V1.5 Pro Image To Video](https://doitong.com/developers/models/bytedance/seedance/v1.5/pro/image-to-video.md): `bytedance/seedance/v1.5/pro/image-to-video`. Seedance 1.5 Pro image-to-video that adds generated audio and start/end frame control. from $0.0117 / second of output video. - [CogVideoX-5B · Image to Video](https://doitong.com/developers/models/cogvideox-5b/image-to-video.md): `cogvideox-5b/image-to-video`. CogVideoX-5B variant that animates a starting image using a text prompt. $0.20 / video. - [Cosmos Predict 2.5 2B · Image to Video](https://doitong.com/developers/models/cosmos-predict-2.5/image-to-video.md): `cosmos-predict-2.5/image-to-video`. Cosmos Predict 2.5 2B clip generation that uses an input image as the first frame. $0.20 / video. - [Gemini Omni Flash · Image to Video](https://doitong.com/developers/models/google/gemini-omni-flash/image-to-video.md): `google/gemini-omni-flash/image-to-video`. Animates one still image into a video with audio, guided by a motion prompt. from $1.276 / run (estimated per run). - [Grok Imagine Video 1.5 Lite Image to Video](https://doitong.com/developers/models/xai/grok-imagine-video/v1.5/lite/image-to-video.md): `xai/grok-imagine-video/v1.5/lite/image-to-video`. Lite 1.5 image animation with durations up to 15 seconds and a 1080p resolution option. from $0.02 / second of output video. - Hailuo 02 (MiniMax), from $0.102: - [MiniMax Hailuo 02 \[Pro\] (Image to Video)](https://doitong.com/developers/models/minimax/hailuo-02/pro/image-to-video.md): `minimax/hailuo-02/pro/image-to-video`. $0.48 / run (estimated per run). - [MiniMax Hailuo 02 \[Standard\] (Image to Video)](https://doitong.com/developers/models/minimax/hailuo-02/standard/image-to-video.md): `minimax/hailuo-02/standard/image-to-video`. from $0.017 / second (6 s ≈ $0.102). - [Minimax · Hailuo 02 Fast · Image to Video](https://doitong.com/developers/models/minimax/hailuo-02-fast/image-to-video.md): `minimax/hailuo-02-fast/image-to-video`. $0.017 / second (6 s ≈ $0.102). - [Happy Horse 1.1 Image to Video](https://doitong.com/developers/models/alibaba/happy-horse/v1.1/image-to-video.md): `alibaba/happy-horse/v1.1/image-to-video`. Happy Horse 1.1 image-to-video, with 3 to 15 second clips and a 20 MB image limit. from $0.14 / second (5 s ≈ $0.70). - [Hunyuan Video Image-to-Video Inference](https://doitong.com/developers/models/hunyuan-video-image-to-video.md): `hunyuan-video-image-to-video`. Animates a still image into video, with a stability toggle that trades motion for fewer artifacts. $0.40 / video. - [Hunyuan Video V1.5 · Image to Video](https://doitong.com/developers/models/hunyuan-video-v1.5/image-to-video.md): `hunyuan-video-v1.5/image-to-video`. Version 1.5 image-to-video with negative prompt, prompt expansion and up to 121 frames. $0.075 / run (estimated per run). - [Kandinsky 6.0 Lite · Image to Video](https://doitong.com/developers/models/kandinsky6-lite/image-to-video.md): `kandinsky6-lite/image-to-video`. Lightweight Kandinsky 6.0 image-to-video with generated audio track and optional upscaling. from $0.085 / run. - [Kandinsky 6.0 Pro · Image to Video](https://doitong.com/developers/models/kandinsky6-pro/image-to-video.md): `kandinsky6-pro/image-to-video`. Animates a start-frame image into a video with audio, negative prompt and guidance control; Pro tier. from $0.252 / run. - [Kandinsky5 Pro · Image to Video](https://doitong.com/developers/models/kandinsky5-pro/image-to-video.md): `kandinsky5-pro/image-to-video`. Kandinsky 5 Pro animation of a reference image into video at 512P or 1024P. from $0.20 / video. - Kling O3 (Kling), from $0.42: - [Kling O3 Image to Video · Pro](https://doitong.com/developers/models/kling-video/o3/pro/image-to-video.md): `kling-video/o3/pro/image-to-video`. from $0.112 / second (5 s ≈ $0.56). - [Kling O3 Image to Video · Standard](https://doitong.com/developers/models/kling-video/o3/standard/image-to-video.md): `kling-video/o3/standard/image-to-video`. from $0.084 / second (5 s ≈ $0.42). - [Kling Video · O3 · 4k · Image to Video](https://doitong.com/developers/models/kling-video/o3/4k/image-to-video.md): `kling-video/o3/4k/image-to-video`. $0.42 / second (5 s ≈ $2.10). - [Kling Video v2.6 Image to Video](https://doitong.com/developers/models/kling-video/v2.6/pro/image-to-video.md): `kling-video/v2.6/pro/image-to-video`. v2.6 image-to-video with optional end frame, native audio generation and voice ID references. from $0.07 / second (5 s ≈ $0.35). - Kling Video v25 (Kling), from $0.21: - [Kling Video · v2.5 Turbo · Pro · Image to Video](https://doitong.com/developers/models/kling-video/v2.5-turbo/pro/image-to-video.md): `kling-video/v2.5-turbo/pro/image-to-video`. $0.07 / second (5 s ≈ $0.35). - [Kling Video · v2.5 Turbo · Standard · Image to Video](https://doitong.com/developers/models/kling-video/v2.5-turbo/standard/image-to-video.md): `kling-video/v2.5-turbo/standard/image-to-video`. $0.042 / second (5 s ≈ $0.21). - Kling Video V3 (Kling), from $0.56: - [Kling Video V3 Standard Turbo Image to Video](https://doitong.com/developers/models/kling-video/v3/turbo/standard/image-to-video.md): `kling-video/v3/turbo/standard/image-to-video`. $0.112 / second (5 s ≈ $0.56). - [Kling Video V3 Turbo Pro Image to Video](https://doitong.com/developers/models/kling-video/v3/turbo/pro/image-to-video.md): `kling-video/v3/turbo/pro/image-to-video`. $0.14 / second (5 s ≈ $0.70). - LongCat Video (Meituan), from $0.025: - [LongCat Video · Image to Video · 480p](https://doitong.com/developers/models/longcat-video/image-to-video/480p.md): `longcat-video/image-to-video/480p`. $0.025 / second of output video. - [LongCat Video · Image to Video · 720p](https://doitong.com/developers/models/longcat-video/image-to-video/720p.md): `longcat-video/image-to-video/720p`. $0.04 / second of output video. - LongCat Video Distilled (Meituan), from $0.005: - [LongCat Video Distilled · Image to Video · 480p](https://doitong.com/developers/models/longcat-video/distilled/image-to-video/480p.md): `longcat-video/distilled/image-to-video/480p`. $0.005 / second of output video. - [LongCat Video Distilled · Image to Video · 720p](https://doitong.com/developers/models/longcat-video/distilled/image-to-video/720p.md): `longcat-video/distilled/image-to-video/720p`. $0.01 / second of output video. - [LTX Video (preview) · Image to Video](https://doitong.com/developers/models/ltx-video/image-to-video.md): `ltx-video/image-to-video`. Preview LTX Video 0.9.1 that animates a single image guided by a text prompt. $0.02 / video. - [LTX Video-0.9.7 13B Distilled · Image to Video](https://doitong.com/developers/models/ltx-video-13b-distilled/image-to-video.md): `ltx-video-13b-distilled/image-to-video`. Image-to-video with the older 0.9.7 distilled 13B model from an image and a prompt. from $0.04 / second of output video. - LTX-2.3 22B Distilled (Lightricks), from $0.002: - [LTX-2.3 22B Distilled · Image to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/image-to-video.md): `ltx-2.3-22b/distilled/image-to-video`. $0.00121 / megapixel of output video. - [LTX-2.3 22B Distilled · Image to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/distilled/image-to-video/lora.md): `ltx-2.3-22b/distilled/image-to-video/lora`. $0.00141 / megapixel of output video. - [LTX-Video 13B 0.9.8 Distilled · Image to Video](https://doitong.com/developers/models/ltxv-13b-098-distilled/image-to-video.md): `ltxv-13b-098-distilled/image-to-video`. Image-to-video with the 0.9.8 distilled 13B model, starting from a supplied image and prompt. from $0.02 / second of output video. - [MAGI-1 (Distilled) · Image to Video](https://doitong.com/developers/models/magi-distilled/image-to-video.md): `magi-distilled/image-to-video`. Animates a still image as the first frame of a 96 to 192 frame video guided by a prompt. from $0.08 / second of output video. - MiniMax (Hailuo AI) Video 01 (MiniMax), from $0.50: - [MiniMax (Hailuo AI) Video 01 Director - Image to Video](https://doitong.com/developers/models/minimax/video-01-director/image-to-video.md): `minimax/video-01-director/image-to-video`. $0.50 / video. - [MiniMax (Hailuo AI) Video 01 Subject Reference](https://doitong.com/developers/models/minimax/video-01-subject-reference.md): `minimax/video-01-subject-reference`. $0.50 / video. - [MiniMax (Hailuo AI) Video 01 · Image to Video](https://doitong.com/developers/models/minimax/video-01/image-to-video.md): `minimax/video-01/image-to-video`. $0.50 / video. - [MiniMax (Hailuo AI) Video 01 · Video 01 Live · Image to Video](https://doitong.com/developers/models/minimax/video-01-live/image-to-video.md): `minimax/video-01-live/image-to-video`. $0.50 / video. - [MiniMax H3 Image to Video LoRA](https://doitong.com/developers/models/minimax/h3/image-to-video/lora.md): `minimax/h3/image-to-video/lora`. Animates a still image as the first frame, with 1 to 3 LoRA adapters for subject consistency and optional end frame. from $0.0625 / second (5 s ≈ $0.313). - MiniMax Hailuo 2.3 (MiniMax), from $0.19: - [MiniMax Hailuo 2.3 \[Pro\] (Image to Video)](https://doitong.com/developers/models/minimax/hailuo-2.3/pro/image-to-video.md): `minimax/hailuo-2.3/pro/image-to-video`. $0.49 / run (estimated per run). - [MiniMax Hailuo 2.3 \[Standard\] (Image to Video)](https://doitong.com/developers/models/minimax/hailuo-2.3/standard/image-to-video.md): `minimax/hailuo-2.3/standard/image-to-video`. from $0.28 / request. - [MiniMax Hailuo 2.3 Fast \[Pro\] (Image to Video)](https://doitong.com/developers/models/minimax/hailuo-2.3-fast/pro/image-to-video.md): `minimax/hailuo-2.3-fast/pro/image-to-video`. $0.33 / video. - [MiniMax Hailuo 2.3 Fast \[Standard\] (Image to Video)](https://doitong.com/developers/models/minimax/hailuo-2.3-fast/standard/image-to-video.md): `minimax/hailuo-2.3-fast/standard/image-to-video`. from $0.19 / request. - [Ovi](https://doitong.com/developers/models/ovi/image-to-video.md): `ovi/image-to-video`. Animates a still image into a video with audio, guided by a text prompt. $0.20 / video. - [Seedance 2.0 US Image to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/us/image-to-video.md): `bytedance/seedance-2.0/us/image-to-video`. Seedance 2.0 image-to-video reaching 4k, with start and end frames and clips of 4 to 15 seconds. from $0.141 / second (4 s ≈ $0.564). - [Seedance 2.5 US Image to Video](https://doitong.com/developers/models/bytedance/seedance-2.5/us/image-to-video.md): `bytedance/seedance-2.5/us/image-to-video`. Animates a still image into a clip with generated audio, optional end frame, 480p to 1080p output. $0.0107 / 1000 tokens (charged by usage, up to $6.944 per run for the example input; the rest is refunded). - Seedance v1 (ByteDance), from $0.01: - [Bytedance Seedance V1 Pro Fast Image To Video](https://doitong.com/developers/models/bytedance/seedance/v1/pro/fast/image-to-video.md): `bytedance/seedance/v1/pro/fast/image-to-video`. from $0.00972 / second of output video. - [Seedance 1.0 Pro · Image to Video](https://doitong.com/developers/models/bytedance/seedance/v1/pro/image-to-video.md): `bytedance/seedance/v1/pro/image-to-video`. from $0.0243 / second of output video. - Vidu Q1 (Vidu), from $0.40: - [Vidu Image to Video · Q1](https://doitong.com/developers/models/vidu/q1/image-to-video.md): `vidu/q1/image-to-video`. $0.40 / run (estimated per run). - [Vidu Start End to Video](https://doitong.com/developers/models/vidu/q1/start-end-to-video.md): `vidu/q1/start-end-to-video`. $0.40 / run (estimated per run). - Vidu Q3 (Vidu), from $0.175: - [Vidu · Q3 · Image to Video](https://doitong.com/developers/models/vidu/q3/image-to-video.md): `vidu/q3/image-to-video`. from $0.07 / second (5 s ≈ $0.35). - [Vidu · Q3 · Image to Video · Turbo](https://doitong.com/developers/models/vidu/q3/image-to-video/turbo.md): `vidu/q3/image-to-video/turbo`. from $0.035 / second (5 s ≈ $0.175). - [Wan 3.0 Prime · Image to Video](https://doitong.com/developers/models/alibaba/wan-3.0-prime/image-to-video.md): `alibaba/wan-3.0-prime/image-to-video`. Image-to-video with a required start frame, optional end frame, audio and clips up to 30 seconds. from $0.068 / second (5 s ≈ $0.34). - [Wan · v2.2 A14b · Image to Video · Turbo](https://doitong.com/developers/models/wan/v2.2-a14b/image-to-video/turbo.md): `wan/v2.2-a14b/image-to-video/turbo`. Turbo A14B image-to-video with a short parameter list: image, prompt, resolution and optional end frame. from $0.05 / video. - [Alibaba V2.6 · Image to Video · Flash](https://doitong.com/developers/models/wan/v2.6/image-to-video/flash.md): `wan/v2.6/image-to-video/flash`. Flash image-to-video that animates a first-frame image for 5, 10 or 15 seconds, with optional audio input. from $0.05 / second (5 s ≈ $0.25). - [Lynx](https://doitong.com/developers/models/bytedance/lynx.md): `bytedance/lynx`. Image-to-video that keeps a subject's identity consistent, with 480p to 720p and 9 to 81 frames. $0.60 / second of output video. - [Creatify Aurora](https://doitong.com/developers/models/creatify/aurora.md): `creatify/aurora`. Avatar video model that animates an image so it speaks or sings along to supplied audio. from $0.07 / second of input audio. - [Davinci Magihuman](https://doitong.com/developers/models/davinci-magihuman.md): `davinci-magihuman`. Image-to-video with synchronized audio and lip-sync, resolutions from 256p to 1080p, up to 30 seconds. $0.05 / second (5 s ≈ $0.25). - [FILM](https://doitong.com/developers/models/film.md): `film`. Interpolates between a start and an end image, outputting in-between frames as images or a video. $0.0013 / second of processing time (charged by usage, up to $4.68 per run for the example input; the rest is refunded). - Framepack (Open model), from $0.134: - [Framepack](https://doitong.com/developers/models/framepack.md): `framepack`. from $0.134 / run (estimated per run). - [Framepack F1](https://doitong.com/developers/models/framepack/f1.md): `framepack/f1`. from $0.134 / run (estimated per run). - [Framepack · FLF2V](https://doitong.com/developers/models/framepack/flf2v.md): `framepack/flf2v`. from $0.134 / run (estimated per run). - [High Quality Stable Video Diffusion](https://doitong.com/developers/models/stable-video.md): `stable-video`. Animates a single still image into a short clip with adjustable motion level, noise and frame rate. $0.075 / video. - Kling O1 (Kling), from $0.42: - [Kling O1 First Frame Last Frame to Video \[Pro\]](https://doitong.com/developers/models/kling-video/o1/image-to-video.md): `kling-video/o1/image-to-video`. $0.112 / second (5 s ≈ $0.56). - [Kling O1 First Frame Last Frame to Video \[Standard\]](https://doitong.com/developers/models/kling-video/o1/standard/image-to-video.md): `kling-video/o1/standard/image-to-video`. $0.084 / second (5 s ≈ $0.42). - [Marey Realism V1.5 · I2V](https://doitong.com/developers/models/moonvalley/marey/i2v.md): `moonvalley/marey/i2v`. Marey image-to-video that starts from your image as first frame, 5s or 10s, five dimensions. $0.30 / second (5 s ≈ $1.50). - Pika (Pika), from $0.20: - [Pika](https://doitong.com/developers/models/pika/v2.2/pikaframes.md): `pika/v2.2/pikaframes`. from $0.04 / second of output video. - [Pika Image to Video (v2.1)](https://doitong.com/developers/models/pika/v2.1/image-to-video.md): `pika/v2.1/image-to-video`. $0.40 / video. - [Pika Image to Video (v2.2)](https://doitong.com/developers/models/pika/v2.2/image-to-video.md): `pika/v2.2/image-to-video`. from $0.20 / video. - [Pika Image to Video Turbo (v2)](https://doitong.com/developers/models/pika/v2/turbo/image-to-video.md): `pika/v2/turbo/image-to-video`. $0.20 / video. - [Pika Scenes (v2.2)](https://doitong.com/developers/models/pika/v2.2/pikascenes.md): `pika/v2.2/pikascenes`. from $0.20 / video. - [Pixelcut Looping Video](https://doitong.com/developers/models/pixelcut/looping-video.md): `pixelcut/looping-video`. Turns a product photo into a looping clip that starts and ends on the source image, with subtle motion or a 360° spin. from $0.08 / second (5 s ≈ $0.40). - PixVerse (PixVerse), from $0.15: - [PixVerse Swap](https://doitong.com/developers/models/pixverse/swap.md): `pixverse/swap`. from $0.15 / run. - [PixVerse V3.5 Effects](https://doitong.com/developers/models/pixverse/v3.5/effects.md): `pixverse/v3.5/effects`. from $0.15 / run. - [PixVerse V3.5 Image To Video](https://doitong.com/developers/models/pixverse/v3.5/image-to-video.md): `pixverse/v3.5/image-to-video`. from $0.15 / run. - [PixVerse V3.5 Image To Video Fast](https://doitong.com/developers/models/pixverse/v3.5/image-to-video/fast.md): `pixverse/v3.5/image-to-video/fast`. from $0.30 / request. - [PixVerse V3.5 Transition](https://doitong.com/developers/models/pixverse/v3.5/transition.md): `pixverse/v3.5/transition`. from $0.15 / run. - [PixVerse V4 Effects](https://doitong.com/developers/models/pixverse/v4/effects.md): `pixverse/v4/effects`. from $0.15 / run. - [PixVerse V4 Image To Video](https://doitong.com/developers/models/pixverse/v4/image-to-video.md): `pixverse/v4/image-to-video`. from $0.15 / run. - [PixVerse V4 Image To Video Fast](https://doitong.com/developers/models/pixverse/v4/image-to-video/fast.md): `pixverse/v4/image-to-video/fast`. from $0.30 / request. - PixVerse C1 (PixVerse), from $0.15: - [PixVerse C1 Image To Video](https://doitong.com/developers/models/pixverse/c1/image-to-video.md): `pixverse/c1/image-to-video`. from $0.03 / second (5 s ≈ $0.15). - [PixVerse C1 Transition](https://doitong.com/developers/models/pixverse/c1/transition.md): `pixverse/c1/transition`. from $0.03 / second (5 s ≈ $0.15). - PixVerse V5 (PixVerse), from $0.15: - [PixVerse V5 Image To Video](https://doitong.com/developers/models/pixverse/v5/image-to-video.md): `pixverse/v5/image-to-video`. from $0.15 / run. - [PixVerse V5 Transition](https://doitong.com/developers/models/pixverse/v5/transition.md): `pixverse/v5/transition`. from $0.15 / run. - [PixVerse V5 Effects](https://doitong.com/developers/models/pixverse/v5/effects.md): `pixverse/v5/effects`. PixVerse v5 image-to-video effects: pick a preset effect and animate a single photo in 5 or 8 seconds. from $0.15 / run. - PixVerse V5.5 (PixVerse), from $0.15: - [PixVerse V5.5 Effects](https://doitong.com/developers/models/pixverse/v5.5/effects.md): `pixverse/v5.5/effects`. from $0.15 / run. - [PixVerse V5.5 Image To Video](https://doitong.com/developers/models/pixverse/v5.5/image-to-video.md): `pixverse/v5.5/image-to-video`. from $0.15 / run. - [PixVerse V5.5 Transition](https://doitong.com/developers/models/pixverse/v5.5/transition.md): `pixverse/v5.5/transition`. from $0.45 / run. - PixVerse V5.6 (PixVerse), from $0.35: - [PixVerse V5.6 Image To Video](https://doitong.com/developers/models/pixverse/v5.6/image-to-video.md): `pixverse/v5.6/image-to-video`. from $0.35 / run. - [PixVerse V5.6 Transition](https://doitong.com/developers/models/pixverse/v5.6/transition.md): `pixverse/v5.6/transition`. from $0.35 / run. - [RIFE](https://doitong.com/developers/models/rife.md): `rife`. Interpolates between a start and end image, returning in-between frames as images or a video. $0.0013 / second of processing time (charged by usage, up to $4.68 per run for the example input; the rest is refunded). - [Stable Video Diffusion Turbo](https://doitong.com/developers/models/fast-svd-lcm.md): `fast-svd-lcm`. Faster Stable Video Diffusion that animates an image in as few as 4 steps. $0.025 / run (estimated per run). - Vidu (Vidu), from $0.20: - [Vidu Image to Video](https://doitong.com/developers/models/vidu/image-to-video.md): `vidu/image-to-video`. $0.20 / request. - [Vidu Start-End to Video](https://doitong.com/developers/models/vidu/start-end-to-video.md): `vidu/start-end-to-video`. $0.20 / request. - [Vidu Q4](https://doitong.com/developers/models/vidu/q4/image-to-video.md): `vidu/q4/image-to-video`. Q4 image-to-video from a first frame, 3-16 seconds, resolutions up to 4K, with native audio. from $0.0315 / second (5 s ≈ $0.158). - Wan 2.1 (Alibaba), from $0.20: - [Wan Effects](https://doitong.com/developers/models/wan-effects.md): `wan-effects`. $0.35 / video. - [Wan-2.1 First-Last-Frame-to-Video](https://doitong.com/developers/models/wan-flf2v.md): `wan-flf2v`. from $0.20 / video. - [Wan-2.1 Image-to-Video](https://doitong.com/developers/models/wan-i2v.md): `wan-i2v`. from $0.20 / video. - [Wan-2.1 Pro Image-to-Video](https://doitong.com/developers/models/wan-pro/image-to-video.md): `wan-pro/image-to-video`. $0.80 / video. - [Wan-2.1 Image-to-Video with LoRAs](https://doitong.com/developers/models/wan-i2v-lora.md): `wan-i2v-lora`. Wan 2.1 image-to-video with custom LoRA support, optional reversed playback and turbo mode. $0.75 / video. - [AMT Frame Interpolation](https://doitong.com/developers/models/amt-interpolation/frame-interpolation.md): `amt-interpolation/frame-interpolation`. Builds a video by interpolating between a list of still frames you provide. $0.000575 / second of processing time (charged by usage, up to $2.07 per run for the example input; the rest is refunded). - Flux 3 (Black Forest Labs), from $0.30: - [Flux 3 First Last Frame to Video Draft](https://doitong.com/developers/models/blackforestlabs/flux-3/first-last-frame-to-video/draft.md): `blackforestlabs/flux-3/first-last-frame-to-video/draft`. $0.06 / second (5 s ≈ $0.30). - [Flux 3 Image To Video Draft](https://doitong.com/developers/models/blackforestlabs/flux-3/image-to-video/draft.md): `blackforestlabs/flux-3/image-to-video/draft`. $0.06 / second (5 s ≈ $0.30). - [Flux 3 Keyframes To Video Draft](https://doitong.com/developers/models/blackforestlabs/flux-3/keyframes-to-video/draft.md): `blackforestlabs/flux-3/keyframes-to-video/draft`. $0.06 / second (5 s ≈ $0.30). - [Gemini Omni Flash 1.1 Image to Video](https://doitong.com/developers/models/google/gemini-omni-flash/v1.1/image-to-video.md): `google/gemini-omni-flash/v1.1/image-to-video`. Animates a first frame into video with sound, with optional end frame and 3-10 second length. from $0.03 / second (8 s ≈ $0.24). - [H3 Max Turbo Image to Video](https://doitong.com/developers/models/minimax/h3-max-turbo/image-to-video.md): `minimax/h3-max-turbo/image-to-video`. Turbo variant that animates a first and/or last frame image into a video, with optional pinned audio. from $0.0163 / second of output video. - Hailuo 03 New Turbo (MiniMax), from $0.033: - [H3 Max Camera Controls](https://doitong.com/developers/models/minimax/h3-max/camera-controls.md): `minimax/h3-max/camera-controls`. from $0.0325 / second (5 s ≈ $0.163). - [H3 Max Image to Video](https://doitong.com/developers/models/minimax/h3-max/image-to-video.md): `minimax/h3-max/image-to-video`. from $0.0325 / second of output video. - [Happy Horse · Image to Video](https://doitong.com/developers/models/alibaba/happy-horse/image-to-video.md): `alibaba/happy-horse/image-to-video`. Animates a first-frame image into a 3 to 15 second clip at 720p or 1080p, with optional prompt. from $0.14 / second (5 s ≈ $0.70). - LTX 2.3 (Lightricks), from $0.36: - [LTX 2.3 Video Fast · Image to Video](https://doitong.com/developers/models/ltx-2.3/image-to-video/fast.md): `ltx-2.3/image-to-video/fast`. from $0.06 / second (6 s ≈ $0.36). - [LTX 2.3 Video Pro · Image to Video](https://doitong.com/developers/models/ltx-2.3/image-to-video.md): `ltx-2.3/image-to-video`. from $0.08 / second (6 s ≈ $0.48). - LTX 2.3 22b (Lightricks), from $0.002: - [LTX-2.3 22B · Image to Video](https://doitong.com/developers/models/ltx-2.3-22b/image-to-video.md): `ltx-2.3-22b/image-to-video`. $0.00161 / megapixel of output video. - [LTX-2.3 22B · Image to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/image-to-video/lora.md): `ltx-2.3-22b/image-to-video/lora`. $0.00181 / megapixel of output video. - LTX 2.3 Quality (Lightricks), from $0.003: - [Ltx 2.3 Quality · Image to Video](https://doitong.com/developers/models/ltx-2.3-quality/image-to-video.md): `ltx-2.3-quality/image-to-video`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Image to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/image-to-video/lora.md): `ltx-2.3-quality/image-to-video/lora`. $0.00271 / megapixel of output video. - [Ltx 2.3 Quality · Ingredient](https://doitong.com/developers/models/ltx-2.3-quality/ingredient.md): `ltx-2.3-quality/ingredient`. $0.00241 / megapixel of output video. - [Luma Ray 3.2 Image to Video](https://doitong.com/developers/models/luma/agent/ray/v3.2/image-to-video.md): `luma/agent/ray/v3.2/image-to-video`. Ray 3.2 image-to-video with end frame or up to 64 keyframes, looping and optional HDR/EXR output. from $0.03 / second (5 s ≈ $0.15). - PixVerse 45 (PixVerse), from $0.15: - [PixVerse V4.5 Effects](https://doitong.com/developers/models/pixverse/v4.5/effects.md): `pixverse/v4.5/effects`. from $0.15 / run. - [PixVerse V4.5 Image To Video](https://doitong.com/developers/models/pixverse/v4.5/image-to-video.md): `pixverse/v4.5/image-to-video`. from $0.15 / run. - [PixVerse V4.5 Image To Video Fast](https://doitong.com/developers/models/pixverse/v4.5/image-to-video/fast.md): `pixverse/v4.5/image-to-video/fast`. from $0.30 / request. - [PixVerse V4.5 Transition](https://doitong.com/developers/models/pixverse/v4.5/transition.md): `pixverse/v4.5/transition`. from $0.15 / run. - PixVerse V6 (PixVerse), from $0.125: - [PixVerse V6 Image To Video](https://doitong.com/developers/models/pixverse/v6/image-to-video.md): `pixverse/v6/image-to-video`. from $0.025 / second (5 s ≈ $0.125). - [PixVerse V6 Transition](https://doitong.com/developers/models/pixverse/v6/transition.md): `pixverse/v6/transition`. from $0.025 / second (5 s ≈ $0.125). - [Wan · v2.7 · Image to Video](https://doitong.com/developers/models/wan/v2.7/image-to-video.md): `wan/v2.7/image-to-video`. Animates a first-frame image into a 2-15 second clip, with optional last frame, video continuation and audio. from $0.10 / second (5 s ≈ $0.50). - Flux 3 New (Black Forest Labs), from $0.85: - [Flux 3 First Last Frame to Video](https://doitong.com/developers/models/blackforestlabs/flux-3/first-last-frame-to-video.md): `blackforestlabs/flux-3/first-last-frame-to-video`. from $0.17 / second (5 s ≈ $0.85). - [FLUX 3 Image to Video](https://doitong.com/developers/models/blackforestlabs/flux-3/image-to-video.md): `blackforestlabs/flux-3/image-to-video`. from $0.17 / second (5 s ≈ $0.85). - [Flux 3 Image to Video · Keyframes to Video](https://doitong.com/developers/models/blackforestlabs/flux-3/keyframes-to-video.md): `blackforestlabs/flux-3/keyframes-to-video`. from $0.17 / second (5 s ≈ $0.85). - [Ffmpeg Api Images to Video](https://doitong.com/developers/models/ffmpeg-api/images-to-video.md): `ffmpeg-api/images-to-video`. Assembles an ordered list of up to 200 images into an MP4 slideshow video at a chosen frame rate. $0.005 / run (estimated per run). ## Models: Reference to Video (33) - Alibaba v2.6 (Alibaba), from $0.05: - [Alibaba V2.6 · Reference to Video · Flash](https://doitong.com/developers/models/wan/v2.6/reference-to-video/flash.md): `wan/v2.6/reference-to-video/flash`. from $0.05 / second of output video. - [Wan v2.6 Reference to Video](https://doitong.com/developers/models/wan/v2.6/reference-to-video.md): `wan/v2.6/reference-to-video`. from $0.10 / second (5 s ≈ $0.50). - [Vidu · Q2 · Reference to Video · Pro](https://doitong.com/developers/models/vidu/q2/reference-to-video/pro.md): `vidu/q2/reference-to-video/pro`. Q2 Pro reference-to-video using images and up to 2 reference videos, 540p to 1080p, 1-8 seconds. from $0.20 / run. - [Bernini-R Reference to Video](https://doitong.com/developers/models/bernini-r/reference-to-video.md): `bernini-r/reference-to-video`. Generates one continuous video from one to five reference subject images and a prompt. from $0.04 / second of output video. - Grok Imagine (xAI), from $0.05: - [Grok Imagine Reference to Video](https://doitong.com/developers/models/xai/grok-imagine-video/reference-to-video.md): `xai/grok-imagine-video/reference-to-video`. from $0.05 / second of output video. - [Grok Imagine Video 1.5 Reference to Video](https://doitong.com/developers/models/xai/grok-imagine-video/v1.5/reference-to-video.md): `xai/grok-imagine-video/v1.5/reference-to-video`. from $0.08 / second of output video. - [MiniMax H3 Reference to Video](https://doitong.com/developers/models/minimax/h3/reference-to-video.md): `minimax/h3/reference-to-video`. Video from up to 9 image, 3 video and 3 audio references, 5 to 15 seconds, up to 4K. from $0.05 / second of output video. - Seedance 2.0 (ByteDance), from $0.007: - [Seedance 2.0 Fast Reference to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/fast/reference-to-video.md): `bytedance/seedance-2.0/fast/reference-to-video`. from $0.113 / second (4 s ≈ $0.452). - [Seedance 2.0 Mini](https://doitong.com/developers/models/bytedance/seedance-2.0/mini/reference-to-video.md): `bytedance/seedance-2.0/mini/reference-to-video`. $0.007 / 1000 tokens. - [Seedance 2.0 Reference to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/reference-to-video.md): `bytedance/seedance-2.0/reference-to-video`. from $0.141 / second (4 s ≈ $0.564). - [Veo3.1 Reference to Video](https://doitong.com/developers/models/veo3.1/reference-to-video.md): `veo3.1/reference-to-video`. Veo 3.1 video that keeps a subject consistent using several reference images, with optional audio. from $0.20 / second (8 s ≈ $1.60). - [Wan 3.0 Reference to Video](https://doitong.com/developers/models/alibaba/wan-3.0/reference-to-video.md): `alibaba/wan-3.0/reference-to-video`. Builds a 2 to 30 second Wan 3.0 clip from up to 10 images, 5 videos and 5 audio clips. from $0.05 / second (5 s ≈ $0.25). - [Gemini Omni Flash · Reference to Video](https://doitong.com/developers/models/google/gemini-omni-flash/reference-to-video.md): `google/gemini-omni-flash/reference-to-video`. Video from a prompt plus 1 to 10 required reference images, with inline image-role tags in the prompt. from $1.282 / run (estimated per run). - [Happy Horse 1.1 Reference to Video](https://doitong.com/developers/models/alibaba/happy-horse/v1.1/reference-to-video.md): `alibaba/happy-horse/v1.1/reference-to-video`. Video from 1-9 reference images, with characters addressed as character1..character9 in the prompt. from $0.14 / second (5 s ≈ $0.70). - [Kling 4.0 Reference to Video](https://doitong.com/developers/models/kling/v4/reference-to-video.md): `kling/v4/reference-to-video`. Generates 3-30 second videos that keep the look of up to 10 reference images, 5 reference videos and 7 elements. from $0.157 / second of output video. - Kling O3 (Kling), from $0.42: - [Kling O3 Reference to Video \[Pro\]](https://doitong.com/developers/models/kling-video/o3/pro/reference-to-video.md): `kling-video/o3/pro/reference-to-video`. from $0.112 / second (5 s ≈ $0.56). - [Kling O3 Reference to Video \[Standard\]](https://doitong.com/developers/models/kling-video/o3/standard/reference-to-video.md): `kling-video/o3/standard/reference-to-video`. from $0.084 / second (5 s ≈ $0.42). - [Kling Video · O3 · 4k · Reference to Video](https://doitong.com/developers/models/kling-video/o3/4k/reference-to-video.md): `kling-video/o3/4k/reference-to-video`. $0.42 / second (5 s ≈ $2.10). - [MiniMax H3 Reference to Video LoRA](https://doitong.com/developers/models/minimax/h3/reference-to-video/lora.md): `minimax/h3/reference-to-video/lora`. H3 reference-to-video with LoRAs, accepting up to 9 images, 3 videos and 3 audio clips. from $0.0625 / second (5 s ≈ $0.313). - [Seedance 2.0 US Reference to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/us/reference-to-video.md): `bytedance/seedance-2.0/us/reference-to-video`. Video from a prompt plus reference images, videos and audio clips, with aspect ratios up to 21:9 and 4k. from $0.0096 / 1000 tokens. - [Seedance 2.5 US Reference to Video](https://doitong.com/developers/models/bytedance/seedance-2.5/us/reference-to-video.md): `bytedance/seedance-2.5/us/reference-to-video`. Seedance 2.5 reference video generation, editing and extension from up to 30 images, 10 videos and 10 audios. $0.0107 / 1000 tokens (charged by usage, up to $6.944 per run for the example input; the rest is refunded). - [Vidu · Q1 · Reference to Video](https://doitong.com/developers/models/vidu/q1/reference-to-video.md): `vidu/q1/reference-to-video`. Q1 video generation that keeps subjects consistent using up to 7 reference images, with optional background music. $0.40 / run (estimated per run). - [Vidu · Q3 · Reference to Video · Mix](https://doitong.com/developers/models/vidu/q3/reference-to-video/mix.md): `vidu/q3/reference-to-video/mix`. Q3 reference-to-video using 1-4 reference images, five aspect ratios, up to 16 seconds with audio. from $0.07 / second (5 s ≈ $0.35). - [Wan 3.0 Prime · Reference to Video](https://doitong.com/developers/models/alibaba/wan-3.0-prime/reference-to-video.md): `alibaba/wan-3.0-prime/reference-to-video`. Multimodal reference-to-video using up to 10 images, 5 clips and 5 audio files, 2-30 seconds. from $0.068 / second (5 s ≈ $0.34). - Kling O1 (Kling), from $0.42: - [Kling O1 Reference Image to Video \[Pro\]](https://doitong.com/developers/models/kling-video/o1/reference-to-video.md): `kling-video/o1/reference-to-video`. $0.112 / second (5 s ≈ $0.56). - [Kling O1 Reference Image to Video \[Standard\]](https://doitong.com/developers/models/kling-video/o1/standard/reference-to-video.md): `kling-video/o1/standard/reference-to-video`. $0.084 / second (5 s ≈ $0.42). - [PixVerse C1 Reference To Video](https://doitong.com/developers/models/pixverse/c1/reference-to-video.md): `pixverse/c1/reference-to-video`. C1 video that keeps characters and backgrounds consistent from up to 7 reference images. from $0.03 / second (5 s ≈ $0.15). - [Vidu Reference to Video](https://doitong.com/developers/models/vidu/reference-to-video.md): `vidu/reference-to-video`. Generates a video from reference images and a prompt, keeping subjects consistent. $0.40 / request. - [Vidu Q4 Reference to Video](https://doitong.com/developers/models/vidu/q4/reference-to-video.md): `vidu/q4/reference-to-video`. Q4 reference-to-video using up to 12 images and 3 voice clips, 3-16 seconds, up to 4K. from $0.0315 / second of output video. - [Gemini Omni Flash 1.1 Reference to Video](https://doitong.com/developers/models/google/gemini-omni-flash/v1.1/reference-to-video.md): `google/gemini-omni-flash/v1.1/reference-to-video`. Version 1.1 video generation guided by up to 10 reference images and 3 short clips, with 360p to 4k output. from $0.03 / second (8 s ≈ $0.24). - [H3 Max Reference to Video](https://doitong.com/developers/models/minimax/h3-max/reference-to-video.md): `minimax/h3-max/reference-to-video`. H3 Max video generation that keeps subjects consistent using reference images, videos and audio clips. from $0.05 / second of output video. - [Happy Horse · Reference to Video](https://doitong.com/developers/models/alibaba/happy-horse/reference-to-video.md): `alibaba/happy-horse/reference-to-video`. Generates video with native audio from a prompt plus 1 to 9 reference images for subject consistency. from $0.14 / second (5 s ≈ $0.70). - [Wan 2.7 Reference to Video](https://doitong.com/developers/models/wan/v2.7/reference-to-video.md): `wan/v2.7/reference-to-video`. Makes video that keeps the subjects of reference images or clips, with multi-subject and multi-shot options. $0.10 / second of output video. ## Models: Video to Video (147) - [Vidu · Q2 · Video Extension · Pro](https://doitong.com/developers/models/vidu/q2/video-extension/pro.md): `vidu/q2/video-extension/pro`. Q2 Pro video extension that continues an existing clip by 2-7 seconds at 720p or 1080p. from $0.15 / run. - [Wan · v2.2 A14b · Video to Video](https://doitong.com/developers/models/wan/v2.2-a14b/video-to-video.md): `wan/v2.2-a14b/video-to-video`. A14B video-to-video that restyles a source clip from a prompt with adjustable strength. from $0.04 / second of output video. - Bernini R (Open model), from $0.04: - [Bernini-R Edit Video](https://doitong.com/developers/models/bernini-r/edit-video.md): `bernini-r/edit-video`. from $0.04 / second of output video. - [Bernini-R Reference Edit Video](https://doitong.com/developers/models/bernini-r/reference-edit-video.md): `bernini-r/reference-edit-video`. from $0.04 / second of output video. - Bria (Bria AI), from $0.14: - [Video · Erase · Keypoints](https://doitong.com/developers/models/bria/video/erase/keypoints.md): `bria/video/erase/keypoints`. $0.14 / second of input video. - [Video · Erase · Mask](https://doitong.com/developers/models/bria/video/erase/mask.md): `bria/video/erase/mask`. $0.14 / second of input video. - [Video · Erase · Prompt](https://doitong.com/developers/models/bria/video/erase/prompt.md): `bria/video/erase/prompt`. $0.14 / second of input video. - [DWPose Pose Prediction · Video](https://doitong.com/developers/models/dwpose/video.md): `dwpose/video`. Runs pose estimation on a whole video and renders a pose or mask video. $0.0006 / second of processing time (charged by usage, up to $2.16 per run for the example input; the rest is refunded). - Sam 3 1 (Meta), from $0.01: - [Sam 3 1 · Video](https://doitong.com/developers/models/sam-3-1/video.md): `sam-3-1/video`. $0.01 / 16 frames of input video. - [Sam 3 1 · Video RLE](https://doitong.com/developers/models/sam-3-1/video-rle.md): `sam-3-1/video-rle`. $0.01 / 16 frames of input video. - Sam3 (Meta), from $0.005: - [Sam 3 · Video](https://doitong.com/developers/models/sam-3/video.md): `sam-3/video`. $0.005 / 16 frames of input video. - [Sam 3 · Video RLE](https://doitong.com/developers/models/sam-3/video-rle.md): `sam-3/video-rle`. $0.005 / 16 frames of input video. - [Segment Anything Model 2 · Video](https://doitong.com/developers/models/sam2/video.md): `sam2/video`. Segments and tracks objects across a video from point or box prompts, with an optional starting mask. $0.001111 / second of processing time (charged by usage, up to $4.00 per run for the example input; the rest is refunded). - [Topaz Denoise Video](https://doitong.com/developers/models/topaz/denoise/video.md): `topaz/denoise/video`. Video denoiser with four Nyx models, tunable noise, compression and halo levels, optional upscale. from $0.00333 / second of input video. - Grok Imagine (xAI), from $0.05: - [Grok Imagine Extend Video](https://doitong.com/developers/models/xai/grok-imagine-video/extend-video.md): `xai/grok-imagine-video/extend-video`. from $0.05 / second of output video. - [Grok Imagine Video · Edit Video](https://doitong.com/developers/models/xai/grok-imagine-video/edit-video.md): `xai/grok-imagine-video/edit-video`. from $0.06 / second of input video. - [AnimateDiff Turbo · Video to Video](https://doitong.com/developers/models/fast-animatediff/turbo/video-to-video.md): `fast-animatediff/turbo/video-to-video`. Fast AnimateDiff Turbo restyling of an input video's first 2 to 4 seconds. $0.00125 / second of processing time (charged by usage, up to $4.50 per run for the example input; the rest is refunded). - [CogVideoX-5B · Video to Video](https://doitong.com/developers/models/cogvideox-5b/video-to-video.md): `cogvideox-5b/video-to-video`. CogVideoX-5B variant that rewrites an existing video from a prompt, with adjustable strength. $0.20 / video. - [Cosmos Predict 2.5 2B · Video to Video](https://doitong.com/developers/models/cosmos-predict-2.5/video-to-video.md): `cosmos-predict-2.5/video-to-video`. Cosmos Predict 2.5 2B generation conditioned on an input video and a text prompt. $0.20 / video. - [AnimateDiff · Video to Video](https://doitong.com/developers/models/fast-animatediff/video-to-video.md): `fast-animatediff/video-to-video`. AnimateDiff restyling of the first 2 to 4 seconds of an input video from a prompt. $0.00125 / second of processing time (charged by usage, up to $4.50 per run for the example input; the rest is refunded). - [Heygen · v3 · Filler Word Removal](https://doitong.com/developers/models/heygen/v3/filler-word-removal.md): `heygen/v3/filler-word-removal`. Cuts filler words and long silences from a video and reports how much time was removed. $0.01 / second of input video. - [Hunyuan Video (Video-to-Video)](https://doitong.com/developers/models/hunyuan-video/video-to-video.md): `hunyuan-video/video-to-video`. Hunyuan Video restyling of an input video, with a strength control for how far it departs from the source. $0.00125 / second of processing time (charged by usage, up to $4.50 per run for the example input; the rest is refunded). - Kling O3 (Kling), from $0.126: - [Kling O3 Edit Video \[Pro\]](https://doitong.com/developers/models/kling-video/o3/pro/video-to-video/edit.md): `kling-video/o3/pro/video-to-video/edit`. $0.168 / second of input video. - [Kling O3 Edit Video \[Standard\]](https://doitong.com/developers/models/kling-video/o3/standard/video-to-video/edit.md): `kling-video/o3/standard/video-to-video/edit`. $0.126 / second of input video. - [Kling O3 Reference Video to Video \[Pro\]](https://doitong.com/developers/models/kling-video/o3/pro/video-to-video/reference.md): `kling-video/o3/pro/video-to-video/reference`. $0.168 / second (3 s ≈ $0.504). - [Kling O3 Reference Video to Video \[Standard\]](https://doitong.com/developers/models/kling-video/o3/standard/video-to-video/reference.md): `kling-video/o3/standard/video-to-video/reference`. $0.126 / second (3 s ≈ $0.378). - [Kling Video 4K Video to Video](https://doitong.com/developers/models/kling-video/o3/4k/video-to-video/reference.md): `kling-video/o3/4k/video-to-video/reference`. $0.42 / second (3 s ≈ $1.26). - [Kling Video 4K Video to Video Edit](https://doitong.com/developers/models/kling-video/o3/4k/video-to-video/edit.md): `kling-video/o3/4k/video-to-video/edit`. $0.42 / second of input video. - Kling Video v2.6 (Kling), from $0.07: - [Kling Video v2.6 Motion Control \[Pro\]](https://doitong.com/developers/models/kling-video/v2.6/pro/motion-control.md): `kling-video/v2.6/pro/motion-control`. $0.112 / second of input video. - [Kling Video v2.6 Motion Control \[Standard\]](https://doitong.com/developers/models/kling-video/v2.6/standard/motion-control.md): `kling-video/v2.6/standard/motion-control`. $0.07 / second of input video. - [Krea Wan 14B](https://doitong.com/developers/models/krea-wan-14b/video-to-video.md): `krea-wan-14b/video-to-video`. Restyles an input video from a text prompt, with a strength control; 16:9 and 480p source only. $0.025 / second of input video. - LTX Video-0.9.5 (Lightricks), from $0.04: - [LTX Video-0.9.5 · Extend](https://doitong.com/developers/models/ltx-video-v095/extend.md): `ltx-video-v095/extend`. $0.04 / video. - [LTX Video-0.9.5 · Multiconditioning](https://doitong.com/developers/models/ltx-video-v095/multiconditioning.md): `ltx-video-v095/multiconditioning`. $0.04 / video. - LTX Video-0.9.7 13B Distilled (Lightricks), from $0.04: - [LTX Video-0.9.7 13B Distilled · Extend](https://doitong.com/developers/models/ltx-video-13b-distilled/extend.md): `ltx-video-13b-distilled/extend`. $0.04 / video. - [LTX Video-0.9.7 13B Distilled · Multiconditioning](https://doitong.com/developers/models/ltx-video-13b-distilled/multiconditioning.md): `ltx-video-13b-distilled/multiconditioning`. from $0.04 / second of output video. - LTX-2.3 22B Distilled (Lightricks), from $0.002: - [LTX-2.3 22B Distilled · Reference Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/reference-video-to-video.md): `ltx-2.3-22b/distilled/reference-video-to-video`. $0.00121 / megapixel of output video. - [LTX-2.3 22B Distilled · Reference Video to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/distilled/reference-video-to-video/lora.md): `ltx-2.3-22b/distilled/reference-video-to-video/lora`. $0.00141 / megapixel of output video. - [LTX-2.3 22B Distilled · Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/video-to-video.md): `ltx-2.3-22b/distilled/video-to-video`. $0.00121 / megapixel of output video. - [LTX-2.3 22B Distilled · Video to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/distilled/video-to-video/lora.md): `ltx-2.3-22b/distilled/video-to-video/lora`. $0.00141 / megapixel of output video. - LTX-Video 13B 0.9.8 Distilled (Lightricks), from $0.02: - [LTX-Video 13B 0.9.8 Distilled · Extend](https://doitong.com/developers/models/ltxv-13b-098-distilled/extend.md): `ltxv-13b-098-distilled/extend`. from $0.02 / second of output video. - [LTX-Video 13B 0.9.8 Distilled · Multiconditioning](https://doitong.com/developers/models/ltxv-13b-098-distilled/multiconditioning.md): `ltxv-13b-098-distilled/multiconditioning`. from $0.02 / second of output video. - [MAGI-1 (Distilled) · Extend Video](https://doitong.com/developers/models/magi-distilled/extend-video.md): `magi-distilled/extend-video`. Continues an existing video from a chosen start frame, producing 96 to 192 new frames. from $0.04 / second of output video. - [FILM · Video](https://doitong.com/developers/models/film/video.md): `film/video`. Frame interpolation for an input video that inserts 1 to 4 in-between frames for smoother motion. $0.0013 / second of processing time (charged by usage, up to $4.68 per run for the example input; the rest is refunded). - Kling O1 (Kling), from $0.126: - [Kling O1 Edit Video \[Pro\]](https://doitong.com/developers/models/kling-video/o1/video-to-video/edit.md): `kling-video/o1/video-to-video/edit`. $0.168 / second of input video. - [Kling O1 Edit Video \[Standard\]](https://doitong.com/developers/models/kling-video/o1/standard/video-to-video/edit.md): `kling-video/o1/standard/video-to-video/edit`. $0.126 / second of input video. - [Kling O1 Reference Video to Video \[Pro\]](https://doitong.com/developers/models/kling-video/o1/video-to-video/reference.md): `kling-video/o1/video-to-video/reference`. $0.168 / second (5 s ≈ $0.84). - [Kling O1 Reference Video to Video \[Standard\]](https://doitong.com/developers/models/kling-video/o1/standard/video-to-video/reference.md): `kling-video/o1/standard/video-to-video/reference`. $0.126 / second (5 s ≈ $0.63). - Marey Realism V1.5 (Moonvalley), from $2.00: - [Marey Realism V1.5 · Motion Transfer](https://doitong.com/developers/models/moonvalley/marey/motion-transfer.md): `moonvalley/marey/motion-transfer`. $2.00 / video. - [Marey Realism V1.5 · Pose Transfer](https://doitong.com/developers/models/moonvalley/marey/pose-transfer.md): `moonvalley/marey/pose-transfer`. $2.00 / video. - [RIFE · Video](https://doitong.com/developers/models/rife/video.md): `rife/video`. Raises the frame rate of an input video by interpolating 1 to 4 frames between existing frames. $0.0013 / second of processing time (charged by usage, up to $4.68 per run for the example input; the rest is refunded). - [AMT Interpolation](https://doitong.com/developers/models/amt-interpolation.md): `amt-interpolation`. Raises the smoothness of an input video by interpolating new in-between frames. $0.000575 / second of processing time (charged by usage, up to $2.07 per run for the example input; the rest is refunded). - [Auto-Captioner](https://doitong.com/developers/models/auto-caption.md): `auto-caption`. Adds speech-based captions to a video with adjustable color, font, size, and position. $0.10 / video. - Bria Video Eraser (Bria AI), from $0.14: - [Bria Video Eraser Erase Mask](https://doitong.com/developers/models/bria/bria_video_eraser/erase/mask.md): `bria/bria_video_eraser/erase/mask`. $0.14 / second of input video. - [Bria Video Eraser · Keypoints](https://doitong.com/developers/models/bria/bria_video_eraser/erase/keypoints.md): `bria/bria_video_eraser/erase/keypoints`. $0.14 / second of input video. - [Bria Video Eraser · Prompt](https://doitong.com/developers/models/bria/bria_video_eraser/erase/prompt.md): `bria/bria_video_eraser/erase/prompt`. $0.14 / second of input video. - [Bytedance Dreamactor V2](https://doitong.com/developers/models/bytedance/dreamactor/v2.md): `bytedance/dreamactor/v2`. Motion transfer from a driving video onto characters in a reference image, including animals and animation. $0.05 / second of input video. - [Depth Anything Video](https://doitong.com/developers/models/depth-anything-video.md): `depth-anything-video`. Estimates per-frame depth maps for an input video, with size, colormap and side-by-side comparison options. $0.04 / second of input video. - [Editto](https://doitong.com/developers/models/editto.md): `editto`. Instruction-based video editing that rewrites a source video from a prompt, with frame, fps and resolution controls. from $0.04 / second of output video. - FFmpeg (Utility), from $0.001: - [FFmpeg API Compose](https://doitong.com/developers/models/ffmpeg-api/compose.md): `ffmpeg-api/compose`. $0.001 / run (estimated per run). - [Ffmpeg Api Merge Audio-Video](https://doitong.com/developers/models/ffmpeg-api/merge-audio-video.md): `ffmpeg-api/merge-audio-video`. $0.0002 / second of input video. - Flux 3 (Black Forest Labs), from $0.60: - [Flux 3 Draft Enhance](https://doitong.com/developers/models/blackforestlabs/flux-3/draft-enhance.md): `blackforestlabs/flux-3/draft-enhance`. $3.48 / run (estimated per run). - [Flux 3 Extend Video Draft](https://doitong.com/developers/models/blackforestlabs/flux-3/extend-video/draft.md): `blackforestlabs/flux-3/extend-video/draft`. $0.12 / second (5 s ≈ $0.60). - [Flux 3 Action](https://doitong.com/developers/models/flux-3-action/so101.md): `flux-3-action/so101`. Robot policy model that predicts SO-101 arm action chunks from camera frames, joint state and an instruction. $0.003 / run (estimated per run). - [Flux 3 FAST Edit Video](https://doitong.com/developers/models/blackforestlabs/flux-3/edit-video.md): `blackforestlabs/flux-3/edit-video`. Prompt-driven video editing that re-renders a short clip while keeping its motion, timing and framing. $0.03 / second of input video. - [Gemini Omni Flash 1.1 Edit](https://doitong.com/developers/models/google/gemini-omni-flash/v1.1/edit.md): `google/gemini-omni-flash/v1.1/edit`. Edits an existing video from a plain-language instruction, with output up to 4k. from $0.03 / second of input video. - [H3 Max Turbo Extend Video](https://doitong.com/developers/models/minimax/h3-max-turbo/extend-video.md): `minimax/h3-max-turbo/extend-video`. Extends a 1.625 to 60 second source video with 0.71 to 15 seconds of prompt-guided new footage. from $0.025 / second (5 s ≈ $0.125). - Hailuo 03 New Turbo (MiniMax), from $0.05: - [H3 Max](https://doitong.com/developers/models/minimax/h3-max/insert-video.md): `minimax/h3-max/insert-video`. from $0.05 / second (5 s ≈ $0.25). - [H3 Max Extend Video](https://doitong.com/developers/models/minimax/h3-max/extend-video.md): `minimax/h3-max/extend-video`. from $0.05 / second of output video. - [H3 Max Recast](https://doitong.com/developers/models/minimax/h3-max/recast.md): `minimax/h3-max/recast`. from $0.30 / second of input video. - [H3 Max Reframe](https://doitong.com/developers/models/minimax/h3-max/reframe-video.md): `minimax/h3-max/reframe-video`. from $0.05 / second of input video. - [H3 Max Relight](https://doitong.com/developers/models/minimax/h3-max/relight.md): `minimax/h3-max/relight`. from $0.05 / second of input video. - [Happy Horse Video Edit](https://doitong.com/developers/models/alibaba/happy-horse/video-edit.md): `alibaba/happy-horse/video-edit`. Edits an existing video from a natural-language prompt, with up to 5 reference images. from $0.28 / second of input video. - ID-V2V (Open model), from $0.20: - [ID-V2V](https://doitong.com/developers/models/id-v2v.md): `id-v2v`. $0.20 / second of output video. - [ID-V2V Relight](https://doitong.com/developers/models/id-v2v/relight.md): `id-v2v/relight`. $0.20 / second of output video. - Kling Video (Kling), from $0.126: - [Kling Video · v3 · Pro · Motion Control](https://doitong.com/developers/models/kling-video/v3/pro/motion-control.md): `kling-video/v3/pro/motion-control`. $0.168 / second of input video. - [Kling Video · v3 · Standard · Motion Control](https://doitong.com/developers/models/kling-video/v3/standard/motion-control.md): `kling-video/v3/standard/motion-control`. $0.126 / second of input video. - Lightx (Open model), from $0.10: - [Lightx · Recamera](https://doitong.com/developers/models/lightx/recamera.md): `lightx/recamera`. $0.10 / second of output video. - [Lightx · Relight](https://doitong.com/developers/models/lightx/relight.md): `lightx/relight`. $0.10 / second of output video. - LTX 2.3 (Lightricks), from $0.10: - [Ltx 2.3](https://doitong.com/developers/models/ltx-2.3/reframe.md): `ltx-2.3/reframe`. from $0.10 / second of input video. - [LTX Video 2.3 Pro · Extend Video](https://doitong.com/developers/models/ltx-2.3/extend-video.md): `ltx-2.3/extend-video`. $0.10 / second (5 s ≈ $0.50). - [LTX Video 2.3 Pro · Retake Video](https://doitong.com/developers/models/ltx-2.3/retake-video.md): `ltx-2.3/retake-video`. $0.10 / second (5 s ≈ $0.50). - LTX 2.3 22b (Lightricks), from $0.002: - [LTX 2.3 22B](https://doitong.com/developers/models/ltx-2.3-22b/reference-video-to-video/lora.md): `ltx-2.3-22b/reference-video-to-video/lora`. $0.00181 / megapixel of output video. - [LTX-2.3 22B · Extend Video](https://doitong.com/developers/models/ltx-2.3-22b/extend-video.md): `ltx-2.3-22b/extend-video`. $0.00161 / megapixel of output video. - [LTX-2.3 22B · Extend Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/extend-video/lora.md): `ltx-2.3-22b/extend-video/lora`. $0.00181 / megapixel of output video. - [LTX-2.3 22B · Reference Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/reference-video-to-video.md): `ltx-2.3-22b/reference-video-to-video`. $0.00161 / megapixel of output video. - [LTX-2.3 22B · Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/video-to-video.md): `ltx-2.3-22b/video-to-video`. $0.00161 / megapixel of output video. - [LTX-2.3 22B · Video to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/video-to-video/lora.md): `ltx-2.3-22b/video-to-video/lora`. $0.00181 / megapixel of output video. - LTX 2.3 Quality (Lightricks), from $0.003: - [Ltx 2.3 Quality · Clean Plate](https://doitong.com/developers/models/ltx-2.3-quality/clean-plate.md): `ltx-2.3-quality/clean-plate`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Colorization](https://doitong.com/developers/models/ltx-2.3-quality/colorization.md): `ltx-2.3-quality/colorization`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Cross Eyed](https://doitong.com/developers/models/ltx-2.3-quality/cross-eyed.md): `ltx-2.3-quality/cross-eyed`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Day to Night](https://doitong.com/developers/models/ltx-2.3-quality/day-to-night.md): `ltx-2.3-quality/day-to-night`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Deblur](https://doitong.com/developers/models/ltx-2.3-quality/deblur.md): `ltx-2.3-quality/deblur`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Decompression](https://doitong.com/developers/models/ltx-2.3-quality/decompression.md): `ltx-2.3-quality/decompression`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Extend Video](https://doitong.com/developers/models/ltx-2.3-quality/extend-video.md): `ltx-2.3-quality/extend-video`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Extend Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/extend-video/lora.md): `ltx-2.3-quality/extend-video/lora`. $0.00271 / megapixel of output video. - [Ltx 2.3 Quality · HDR](https://doitong.com/developers/models/ltx-2.3-quality/hdr.md): `ltx-2.3-quality/hdr`. $0.00271 / megapixel of output video. - [Ltx 2.3 Quality · HDR · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/hdr/lora.md): `ltx-2.3-quality/hdr/lora`. $0.00271 / megapixel of output video. - [LTX 2.3 Quality · Inpaint](https://doitong.com/developers/models/ltx-2.3-quality/inpaint.md): `ltx-2.3-quality/inpaint`. $0.00241 / megapixel of output video. - [LTX 2.3 Quality · Inpaint · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/inpaint/lora.md): `ltx-2.3-quality/inpaint/lora`. $0.00271 / megapixel of output video. - [Ltx 2.3 Quality · Instant Shave](https://doitong.com/developers/models/ltx-2.3-quality/instant-shave.md): `ltx-2.3-quality/instant-shave`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Outpaint](https://doitong.com/developers/models/ltx-2.3-quality/outpaint.md): `ltx-2.3-quality/outpaint`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Outpaint · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/outpaint/lora.md): `ltx-2.3-quality/outpaint/lora`. $0.00271 / megapixel of output video. - [Ltx 2.3 Quality · Reference Video to Video](https://doitong.com/developers/models/ltx-2.3-quality/reference-video-to-video.md): `ltx-2.3-quality/reference-video-to-video`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Reference Video to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/reference-video-to-video/lora.md): `ltx-2.3-quality/reference-video-to-video/lora`. $0.00271 / megapixel of output video. - [Ltx 2.3 Quality · Render to Real](https://doitong.com/developers/models/ltx-2.3-quality/render-to-real.md): `ltx-2.3-quality/render-to-real`. from $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Water Simulation](https://doitong.com/developers/models/ltx-2.3-quality/water-simulation.md): `ltx-2.3-quality/water-simulation`. $0.00241 / megapixel of output video. - [Lucy Restyle](https://doitong.com/developers/models/decart/lucy-restyle.md): `decart/lucy-restyle`. Restyles an existing video from a text prompt, with optional prompt enhancement and a resolution setting. $0.01 / second of input video. - Luma Ray 3.2 (Luma AI), from $0.06: - [Luma Ray 3.2 Reframe](https://doitong.com/developers/models/luma/agent/ray/v3.2/reframe.md): `luma/agent/ray/v3.2/reframe`. from $0.06 / second of input video. - [Luma Ray 3.2 Video to Video](https://doitong.com/developers/models/luma/agent/ray/v3.2/video-to-video.md): `luma/agent/ray/v3.2/video-to-video`. from $0.144 / second (5 s ≈ $0.72). - One To All Animation (Open model), from $0.03: - [One To All Animation · 1.3b](https://doitong.com/developers/models/one-to-all-animation/1.3b.md): `one-to-all-animation/1.3b`. from $0.03 / second of input video. - [One To All Animation · 14b](https://doitong.com/developers/models/one-to-all-animation/14b.md): `one-to-all-animation/14b`. from $0.06 / second of input video. - PixVerse 45 (PixVerse), from $0.15: - [PixVerse Extend](https://doitong.com/developers/models/pixverse/extend.md): `pixverse/extend`. from $0.15 / run. - [PixVerse Extend Fast](https://doitong.com/developers/models/pixverse/extend/fast.md): `pixverse/extend/fast`. from $0.30 / run. - [PixVerse V6 Extend](https://doitong.com/developers/models/pixverse/v6/extend.md): `pixverse/v6/extend`. Continues an existing video by 1 to 15 seconds, following a prompt that describes what happens next. from $0.025 / second (5 s ≈ $0.125). - [Scail 2](https://doitong.com/developers/models/scail-2.md): `scail-2`. Animates a reference character image with motion from a driving video, or swaps it into the original scene. $0.20 / second of input video. - [Seedance 2.5](https://doitong.com/developers/models/bytedance/seedance-2.5/draft/complete.md): `bytedance/seedance-2.5/draft/complete`. Completes a saved Seedance 2.5 draft by regenerating it at 1080p from its draft id. $9.15 / run (estimated per run). - [Topaz Deblur Video](https://doitong.com/developers/models/topaz/deblur/video.md): `topaz/deblur/video`. Motion deblur for video, restoring clarity in fast-moving blurred footage at its original resolution. from $0.00667 / second of input video. - [Topaz Interpolate Video](https://doitong.com/developers/models/topaz/interpolate/video.md): `topaz/interpolate/video`. Frame interpolation for video with Apollo, Chronos or Aion, retiming to 16-120 fps and up to 8x slow motion. from $0.001 / frame of output video. - [Topaz Sdr To Hdr Video](https://doitong.com/developers/models/topaz/sdr-to-hdr/video.md): `topaz/sdr-to-hdr/video`. Converts SDR video to HDR, delivering 10-bit H265 mp4 or ProRes 422 HQ for grading. from $0.2317 / second of input video. - [Void Video Inpainting](https://doitong.com/developers/models/void-video-inpainting.md): `void-video-inpainting`. Removes an object from a video along with its effects on the scene, using a mask video or text mask prompt. from $0.10 / run. - Wan 2.2 VACE Fun A14B (Alibaba), from $0.05: - [Wan 2.2 VACE Fun A14B · Depth](https://doitong.com/developers/models/wan-22-vace-fun-a14b/depth.md): `wan-22-vace-fun-a14b/depth`. from $0.05 / second of output video. - [Wan 2.2 VACE Fun A14B · Inpainting](https://doitong.com/developers/models/wan-22-vace-fun-a14b/inpainting.md): `wan-22-vace-fun-a14b/inpainting`. from $0.05 / second of output video. - [Wan 2.2 VACE Fun A14B · Outpainting](https://doitong.com/developers/models/wan-22-vace-fun-a14b/outpainting.md): `wan-22-vace-fun-a14b/outpainting`. from $0.05 / second of output video. - [Wan 2.2 VACE Fun A14B · Reframe](https://doitong.com/developers/models/wan-22-vace-fun-a14b/reframe.md): `wan-22-vace-fun-a14b/reframe`. from $0.05 / second of output video. - [Wan Motion](https://doitong.com/developers/models/wan-motion.md): `wan-motion`. Character animation that moves a reference image using the motion of a driving video, with pose adaptation. $0.06 / second of input video. - Wan VACE 14B (Alibaba), from $0.04: - [Wan VACE 14B](https://doitong.com/developers/models/wan-vace-14b.md): `wan-vace-14b`. from $0.04 / second of output video. - [Wan VACE 14B · Depth](https://doitong.com/developers/models/wan-vace-14b/depth.md): `wan-vace-14b/depth`. from $0.04 / second of output video. - [Wan VACE 14B · Inpainting](https://doitong.com/developers/models/wan-vace-14b/inpainting.md): `wan-vace-14b/inpainting`. from $0.04 / second of output video. - [Wan VACE 14B · Outpainting](https://doitong.com/developers/models/wan-vace-14b/outpainting.md): `wan-vace-14b/outpainting`. from $0.04 / second of output video. - [Wan VACE 14B · Pose](https://doitong.com/developers/models/wan-vace-14b/pose.md): `wan-vace-14b/pose`. from $0.04 / second of output video. - [Wan VACE 14B · Reframe](https://doitong.com/developers/models/wan-vace-14b/reframe.md): `wan-vace-14b/reframe`. from $0.04 / second of output video. - Wan VACE Apps (Alibaba), from $0.04: - [Wan 2.1 VACE Long Reframe](https://doitong.com/developers/models/wan-vace-apps/long-reframe.md): `wan-vace-apps/long-reframe`. from $0.04 / 2 seconds of input video. - [Wan VACE Video Edit](https://doitong.com/developers/models/wan-vace-apps/video-edit.md): `wan-vace-apps/video-edit`. from $0.05 / second of input video. - Wan-2.2 Animate (Alibaba), from $0.04: - [Wan-2.2 Animate Move](https://doitong.com/developers/models/wan/v2.2-14b/animate/move.md): `wan/v2.2-14b/animate/move`. from $0.04 / second of input video. - [Wan-2.2 Animate Replace](https://doitong.com/developers/models/wan/v2.2-14b/animate/replace.md): `wan/v2.2-14b/animate/replace`. from $0.04 / second of input video. - [Wan · v2.7 · Edit Video](https://doitong.com/developers/models/wan/v2.7/edit-video.md): `wan/v2.7/edit-video`. Wan 2.7 video editing and style transfer from a prompt, with optional reference image and audio handling. from $0.10 / second of output video. - Workflow Utilities (Utility), from $0.005: - [Workflow Utilities Auto Subtitle](https://doitong.com/developers/models/workflow-utilities/auto-subtitle.md): `workflow-utilities/auto-subtitle`. $0.03 / minute of input video. - [Workflow Utilities Blend Video](https://doitong.com/developers/models/workflow-utilities/blend-video.md): `workflow-utilities/blend-video`. $0.001 / second of processing time (charged by usage, up to $3.60 per run for the example input; the rest is refunded). - [Workflow Utilities Interleave Video](https://doitong.com/developers/models/workflow-utilities/interleave-video.md): `workflow-utilities/interleave-video`. $0.00017 / second of processing time (charged by usage, up to $0.612 per run for the example input; the rest is refunded). - [Workflow Utilities Reverse Video](https://doitong.com/developers/models/workflow-utilities/reverse-video.md): `workflow-utilities/reverse-video`. $0.001 / second of processing time (charged by usage, up to $3.60 per run for the example input; the rest is refunded). - [Workflow Utilities Scale Video](https://doitong.com/developers/models/workflow-utilities/scale-video.md): `workflow-utilities/scale-video`. $0.001 / second of processing time (charged by usage, up to $3.60 per run for the example input; the rest is refunded). - [Workflow Utilities Trim Video](https://doitong.com/developers/models/workflow-utilities/trim-video.md): `workflow-utilities/trim-video`. $0.001 / second of processing time (charged by usage, up to $3.60 per run for the example input; the rest is refunded). - [Subtitles](https://doitong.com/developers/models/veed/subtitles.md): `veed/subtitles`. Burns styled subtitles into a video, from auto-transcription or your own SRT, with optional translation. from $0.10 / minute of input video. - [Flux 3 Extend Video](https://doitong.com/developers/models/blackforestlabs/flux-3/extend-video.md): `blackforestlabs/flux-3/extend-video`. Continues an existing MP4 clip past its last frame, with resolutions up to 2160p. from $0.41 / second (5 s ≈ $2.05). - [Sonilo V1.1 Video to Video Music](https://doitong.com/developers/models/sonilo/v1.1/video-to-video-music.md): `sonilo/v1.1/video-to-video-music`. Returns the input video with a generated music track mixed in, with optional speech preserved. $0.009 / second of output audio. - [Ffmpeg Api · Merge Videos](https://doitong.com/developers/models/ffmpeg-api/merge-videos.md): `ffmpeg-api/merge-videos`. Joins two or more videos from URLs into one clip, with optional target frame rate and output resolution. $0.00017 / second of processing time (charged by usage, up to $0.612 per run for the example input; the rest is refunded). - [Mirelo SFX2.0 · Video to Video](https://doitong.com/developers/models/mirelo-ai/sfx2.0/video-to-video.md): `mirelo-ai/sfx2.0/video-to-video`. Adds generated sound effects to an input video and returns it with a new soundtrack, with optional text guidance. $0.01 / second of output audio. ## Models: Lipsync & Avatars (65) - [Wan-2.2 Speech-to-Video 14B](https://doitong.com/developers/models/wan/v2.2-14b/speech-to-video.md): `wan/v2.2-14b/speech-to-video`. Makes a talking video from a still image and an audio file, guided by a text prompt. from $0.10 / second of output video. - LTX 2.5 (Lightricks), from $0.13: - [Ltx 2.5 Audio to Video Fast](https://doitong.com/developers/models/lightricks/ltx-2.5/audio-to-video/fast.md): `lightricks/ltx-2.5/audio-to-video/fast`. $0.13 / second of input audio. - [Ltx 2.5 Audio to Video Pro](https://doitong.com/developers/models/lightricks/ltx-2.5/audio-to-video/pro.md): `lightricks/ltx-2.5/audio-to-video/pro`. $0.17 / second of input audio. - HeyGen v2 (HeyGen), from $0.05: - [Heygen · v2 · Translate · Precision](https://doitong.com/developers/models/heygen/v2/translate/precision.md): `heygen/v2/translate/precision`. $0.10 / second of input video. - [Heygen · v2 · Translate · Speed](https://doitong.com/developers/models/heygen/v2/translate/speed.md): `heygen/v2/translate/speed`. $0.05 / second of input video. - LTX-2.3 22B Distilled (Lightricks), from $0.002: - [LTX-2.3 22B Distilled · Audio to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/audio-to-video.md): `ltx-2.3-22b/distilled/audio-to-video`. $0.00121 / megapixel of output video. - [LTX-2.3 22B Distilled · Audio to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/distilled/audio-to-video/lora.md): `ltx-2.3-22b/distilled/audio-to-video/lora`. $0.00141 / megapixel of output video. - [OmniHuman](https://doitong.com/developers/models/bytedance/omnihuman.md): `bytedance/omnihuman`. Animates a human image to speak or move along with an audio clip, with no extra controls. $0.14 / second of input audio. - [H3 Max Lip Sync Image to Video](https://doitong.com/developers/models/minimax/h3-max/lip-sync/image-to-video.md): `minimax/h3-max/lip-sync/image-to-video`. Turns a portrait image and an audio file into a lip-synced talking video, up to 2K. from $0.05 / second of input audio. - [LTX 2.3 Video Pro · Audio to Video](https://doitong.com/developers/models/ltx-2.3/audio-to-video.md): `ltx-2.3/audio-to-video`. Pro audio-to-video that builds a clip from an audio file, optionally anchored on a first-frame image. $0.10 / second of input audio. - LTX 2.3 22b (Lightricks), from $0.002: - [LTX-2.3 22B · Audio to Video](https://doitong.com/developers/models/ltx-2.3-22b/audio-to-video.md): `ltx-2.3-22b/audio-to-video`. $0.00161 / megapixel of output video. - [LTX-2.3 22B · Audio to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/audio-to-video/lora.md): `ltx-2.3-22b/audio-to-video/lora`. $0.00181 / megapixel of output video. - LTX 2.3 Quality (Lightricks), from $0.003: - [Ltx 2.3 Quality · Audio to Video](https://doitong.com/developers/models/ltx-2.3-quality/audio-to-video.md): `ltx-2.3-quality/audio-to-video`. $0.00241 / megapixel of output video. - [Ltx 2.3 Quality · Audio to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/audio-to-video/lora.md): `ltx-2.3-quality/audio-to-video/lora`. $0.00271 / megapixel of output video. - [PixVerse Lipsync](https://doitong.com/developers/models/pixverse/lipsync.md): `pixverse/lipsync`. Lip-syncs a video to supplied audio or to text-to-speech with a chosen voice. $0.04 / second of output video. - Kling Avatar (Kling), from $0.057: - [Kling AI Avatar](https://doitong.com/developers/models/kling-video/v1/standard/ai-avatar.md): `kling-video/v1/standard/ai-avatar`. $0.0562 / second of input audio. - [Kling AI Avatar 2.0 Pro](https://doitong.com/developers/models/kling-video/ai-avatar/v2/pro.md): `kling-video/ai-avatar/v2/pro`. $0.115 / second of input audio. - [Kling AI Avatar Pro](https://doitong.com/developers/models/kling-video/v1/pro/ai-avatar.md): `kling-video/v1/pro/ai-avatar`. $0.115 / second of input audio. - [Kling AI Avatar v2 Standard](https://doitong.com/developers/models/kling-video/ai-avatar/v2/standard.md): `kling-video/ai-avatar/v2/standard`. $0.0562 / second of input audio. - Sync 3 (Sync Labs), from $8.00: - [Sync Lipsync 3](https://doitong.com/developers/models/sync-lipsync/v3.md): `sync-lipsync/v3`. $8.00 / minute of output video. - [Sync React-1](https://doitong.com/developers/models/sync-lipsync/react-1.md): `sync-lipsync/react-1`. $10.00 / minute of output video. - [sync-3 Avatar Image to Video](https://doitong.com/developers/models/sync-lipsync/v3/image-to-video.md): `sync-lipsync/v3/image-to-video`. $8.00 / minute of input audio. - VEED Fabric (VEED), from $0.08: - [Fabric 1.0](https://doitong.com/developers/models/veed/fabric-1.0/text.md): `veed/fabric-1.0/text`. from $2.40 / run (estimated per run). - [Fabric 1.0 Fast](https://doitong.com/developers/models/veed/fabric-1.0/fast.md): `veed/fabric-1.0/fast`. from $0.10 / second of input audio. - [Lipsync](https://doitong.com/developers/models/veed/lipsync.md): `veed/lipsync`. $0.40 / minute of output video. - [VEED Fabric 1.0](https://doitong.com/developers/models/veed/fabric-1.0.md): `veed/fabric-1.0`. from $0.08 / second of input audio. - AI Avatar (Open model), from $0.20: - [AI Avatar Multi](https://doitong.com/developers/models/ai-avatar/multi.md): `ai-avatar/multi`. from $0.20 / second of output video. - [AI Avatar Multi Text](https://doitong.com/developers/models/ai-avatar/multi-text.md): `ai-avatar/multi-text`. from $0.648 / run (estimated per run). - [AI Avatar Single Text](https://doitong.com/developers/models/ai-avatar/single-text.md): `ai-avatar/single-text`. from $4.688 / run (estimated per run). - Argil Avatar (Argil), from $0.02: - [Avatars Audio to Video](https://doitong.com/developers/models/argil/avatars/audio-to-video.md): `argil/avatars/audio-to-video`. from $0.02 / second of input audio. - [Avatars Text to Video](https://doitong.com/developers/models/argil/avatars/text-to-video.md): `argil/avatars/text-to-video`. $0.0225 / second of generated video (charged by usage, up to $1.058 per run for the example input; the rest is refunded). - Bytedance Omnihuman (ByteDance), from $0.105: - [Bytedance Omnihuman V1.5](https://doitong.com/developers/models/bytedance/omnihuman/v1.5.md): `bytedance/omnihuman/v1.5`. $0.16 / second of input audio. - [Bytedance Omnihuman V2](https://doitong.com/developers/models/bytedance/omnihuman/v2.md): `bytedance/omnihuman/v2`. $0.105 / second of input audio. - [EchoMimic V3](https://doitong.com/developers/models/echomimic-v3.md): `echomimic-v3`. Talking-avatar video generated from a portrait image, an audio track and a text prompt. $0.20 / second of input audio. - [Flashhead](https://doitong.com/developers/models/flashhead.md): `flashhead`. Turns a face image and typed text into a talking-head video using a chosen synthetic voice. $0.068 / run (estimated per run). - [Flashtalk](https://doitong.com/developers/models/flashtalk.md): `flashtalk`. Drives a face image with your own speech audio file to produce a lip-synced avatar video. $0.02 / second of input audio. - [Heygen · Avatar3 · Digital Twin](https://doitong.com/developers/models/heygen/avatar3/digital-twin.md): `heygen/avatar3/digital-twin`. Talking-avatar video from a character and voice config, optionally lip-synced to your own audio. $0.034 / second of input audio. - HeyGen Avatar4 (HeyGen), from $0.10: - [Heygen · Avatar4 · Digital Twin](https://doitong.com/developers/models/heygen/avatar4/digital-twin.md): `heygen/avatar4/digital-twin`. $0.10 / second of input audio. - [Heygen · Avatar4 · Image to Video](https://doitong.com/developers/models/heygen/avatar4/image-to-video.md): `heygen/avatar4/image-to-video`. $0.10 / second of input audio. - Heygen Lipsync (HeyGen), from $0.05: - [Heygen Lipsync - Precision](https://doitong.com/developers/models/heygen/v3/lipsync/precision.md): `heygen/v3/lipsync/precision`. $0.10 / second of output video. - [Heygen Lipsync - Speed](https://doitong.com/developers/models/heygen/v3/lipsync/speed.md): `heygen/v3/lipsync/speed`. $0.05 / second of output video. - [Heygen v5 Digital Twin](https://doitong.com/developers/models/heygen/avatar5/digital-twin.md): `heygen/avatar5/digital-twin`. Avatar V digital twin with 4k output, transparent WebM, background, watermark and SRT captions. $0.10 / second of input audio. - Infinitalk (Meituan), from $0.20: - [Infinitalk](https://doitong.com/developers/models/infinitalk.md): `infinitalk`. from $0.20 / second of output video. - [Infinitalk · Single Text](https://doitong.com/developers/models/infinitalk/single-text.md): `infinitalk/single-text`. from $2.32 / run (estimated per run). - [Infinitalk · Video to Video](https://doitong.com/developers/models/infinitalk/video-to-video.md): `infinitalk/video-to-video`. from $0.30 / second of output video. - Kling LipSync (Kling), from $0.014: - [Kling LipSync Audio-to-Video](https://doitong.com/developers/models/kling-video/lipsync/audio-to-video.md): `kling-video/lipsync/audio-to-video`. $0.014 / second of input video. - [Kling LipSync Text-to-Video](https://doitong.com/developers/models/kling-video/lipsync/text-to-video.md): `kling-video/lipsync/text-to-video`. $0.014 / second of input video. - [LatentSync](https://doitong.com/developers/models/latentsync.md): `latentsync`. Lip-sync video-to-video that matches a video's mouth movement to a supplied audio track. $0.005 / second of output video. - [Live Portrait](https://doitong.com/developers/models/live-portrait.md): `live-portrait`. Animates a portrait image with expressions taken from a driving video, with fine face controls. $0.00125 / second of processing time (charged by usage, up to $4.50 per run for the example input; the rest is refunded). - Longcat Single Avatar (Meituan), from $0.15: - [Longcat Single Avatar · Audio to Video](https://doitong.com/developers/models/longcat-single-avatar/audio-to-video.md): `longcat-single-avatar/audio-to-video`. from $0.15 / second of output video. - [Longcat Single Avatar · Image Audio to Video](https://doitong.com/developers/models/longcat-single-avatar/image-audio-to-video.md): `longcat-single-avatar/image-audio-to-video`. from $0.15 / second of output video. - Mirage Avatar X (Mirage), from $0.30: - [Avatar X](https://doitong.com/developers/models/mirage-api/avatar-x/text-to-video.md): `mirage-api/avatar-x/text-to-video`. $54.00 / run (estimated per run). - [Mirage Avatar X](https://doitong.com/developers/models/mirage-api/avatar-x/reference-to-video.md): `mirage-api/avatar-x/reference-to-video`. $0.30 / second of input audio. - [MuseTalk](https://doitong.com/developers/models/musetalk.md): `musetalk`. Lip-syncs a face in a source video to a supplied audio track. $0.00125 / second of processing time (charged by usage, up to $4.50 per run for the example input; the rest is refunded). - [PixVerse VibeMV](https://doitong.com/developers/models/pixverse/music-video/vibemv.md): `pixverse/music-video/vibemv`. Turns an MP3 or WAV track into a music video with style presets, lyrics subtitles and optional lip sync. from $0.06 / second of input audio. - Sad Talker (Open model), from $0.042: - [Sad Talker](https://doitong.com/developers/models/sadtalker.md): `sadtalker`. $0.00125 / second of processing time (charged by usage, up to $4.50 per run for the example input; the rest is refunded). - [Sad Talker · Reference](https://doitong.com/developers/models/sadtalker/reference.md): `sadtalker/reference`. $0.00125 / second of processing time (charged by usage, up to $4.50 per run for the example input; the rest is refunded). - Sync Lipsync (Sync Labs), from $0.70: - [Sync Lipsync 2.0](https://doitong.com/developers/models/sync-lipsync/v2.md): `sync-lipsync/v2`. from $3.00 / minute of output video. - [sync.so -- lipsync 1.9.0-beta](https://doitong.com/developers/models/sync-lipsync.md): `sync-lipsync`. $0.70 / minute of output video. - [Sync Lipsync](https://doitong.com/developers/models/sync-lipsync/v2/pro.md): `sync-lipsync/v2/pro`. Lip-syncs an existing video to a supplied audio track, keeping teeth and facial details. $5.00 / minute of output video. - VEED Avatars 1 (VEED), from $0.30: - [Avatars · Audio to Video](https://doitong.com/developers/models/veed/avatars/audio-to-video.md): `veed/avatars/audio-to-video`. $0.30 / minute of input audio. - [Avatars · Text to Video](https://doitong.com/developers/models/veed/avatars/text-to-video.md): `veed/avatars/text-to-video`. $0.70 / run (estimated per run). - [VEED Lipsync](https://doitong.com/developers/models/veed/lipsync/v2.md): `veed/lipsync/v2`. Second-generation lipsync that replaces the speech movements in a video to match new audio. $0.07 / second of output video. - [ElevenLabs Dubbing](https://doitong.com/developers/models/elevenlabs/dubbing.md): `elevenlabs/dubbing`. Dubs an audio or video file into a target language, with optional source language and speaker count. $0.60 / minute of input file. - [Mureka 9.5 Lyrics Video](https://doitong.com/developers/models/mureka/api/generate/lyrics-video.md): `mureka/api/generate/lyrics-video`. Creates a lyrics video from a generated or uploaded song, with seven layouts and four aspect ratios. $0.15 / video. ## Models: Upscale (32) - [Ideogram Upscale](https://doitong.com/developers/models/ideogram/upscale.md): `ideogram/upscale`. Image upscaler with prompt guidance and sliders for resemblance and detail. $0.06 / image. - [Fooocus Upscale or Vary](https://doitong.com/developers/models/fooocus/upscale-or-vary.md): `fooocus/upscale-or-vary`. Fooocus tool to upscale an image 1.5x or 2x, or create subtle or strong variations of it. $0.007 / image (estimated per run). - Bria (Bria AI), from $0.04: - [Bria Increase Resolution](https://doitong.com/developers/models/bria/increase-resolution.md): `bria/increase-resolution`. $0.04 / image. - [Upscale](https://doitong.com/developers/models/bria/upscale/creative.md): `bria/upscale/creative`. $0.04 / image. - [Video · Increase Resolution](https://doitong.com/developers/models/bria/video/increase-resolution.md): `bria/video/increase-resolution`. $0.14 / second of input video. - Topaz Image Upscale (Topaz Labs), from $0.01: - [Topaz Image Upscale](https://doitong.com/developers/models/topaz/upscale/image/precision.md): `topaz/upscale/image/precision`. $0.08 / 24 megapixels of output image. - [Topaz Upscale Image Creative](https://doitong.com/developers/models/topaz/upscale/image/creative.md): `topaz/upscale/image/creative`. $0.08 / 2 megapixels of output image. - [Topaz Upscale Image Generative](https://doitong.com/developers/models/topaz/upscale/image/generative.md): `topaz/upscale/image/generative`. from $0.01 / megapixel of output image. - [Topaz Upscale Image Transparent](https://doitong.com/developers/models/topaz/upscale/image/transparent.md): `topaz/upscale/image/transparent`. $0.08 / 24 megapixels of output image. - Topaz Video Upscale (Topaz Labs), from $0.10: - [Topaz Upscale Video Creative](https://doitong.com/developers/models/topaz/upscale/video/creative.md): `topaz/upscale/video/creative`. from $0.30 / second of input video. - [Topaz Upscale Video Generative](https://doitong.com/developers/models/topaz/upscale/video/generative.md): `topaz/upscale/video/generative`. from $0.06 / second of input video. - [Topaz Video Upscale](https://doitong.com/developers/models/topaz/upscale/video/precision.md): `topaz/upscale/video/precision`. from $0.00667 / second of input video. - [AuraSR](https://doitong.com/developers/models/aura-sr.md): `aura-sr`. Upscales an image, 4x by default, with selectable v1 or v2 checkpoint and optional overlapping tiles. $0.001111 / second of processing time (charged by usage, up to $1.00 per run for the example input; the rest is refunded). - [Bytedance Upscaler Upscale Video](https://doitong.com/developers/models/bytedance-upscaler/upscale/video.md): `bytedance-upscaler/upscale/video`. Upscales video to as high as 8K with presets, quality tiers, frame-rate and bit-depth options. from $0.0072 / second of input video. - [Chrono Edit Lora Gallery · Upscaler](https://doitong.com/developers/models/chrono-edit-lora-gallery/upscaler.md): `chrono-edit-lora-gallery/upscaler`. Image upscaler and cleanup with a 1x to 4x factor, built on the Chrono Edit LoRA setup. $0.03 / image. - [Clarity Upscaler](https://doitong.com/developers/models/clarity-upscaler.md): `clarity-upscaler`. Diffusion image upscaler with creativity and resemblance controls, scaling 1x to 4x. $0.03 / megapixel of output image. - [Creative Upscaler](https://doitong.com/developers/models/creative-upscaler.md): `creative-upscaler`. Diffusion-based creative upscaler that adds detail, with SD 1.5 or SDXL base and shape control. $0.00125 / second of processing time (charged by usage, up to $1.125 per run for the example input; the rest is refunded). - Crystal Upscaler (Clarity AI), from $0.016: - [Crystal Upscaler](https://doitong.com/developers/models/clarityai/crystal-upscaler.md): `clarityai/crystal-upscaler`. $0.016 / megapixel of output image. - [Crystal Upscaler \[Video\]](https://doitong.com/developers/models/clarityai/crystal-video-upscaler.md): `clarityai/crystal-video-upscaler`. from $0.10 / megapixel of output video. - [DRCT-Super-Resolution](https://doitong.com/developers/models/drct-super-resolution.md): `drct-super-resolution`. Image upscaler that enlarges a picture by a configurable integer factor, 4x by default. $0.0045 / megapixel of output image. - [Flashvsr](https://doitong.com/developers/models/flashvsr/upscale/video.md): `flashvsr/upscale/video`. Video upscaler that enlarges footage by a factor of 1 to 4, with optional audio passthrough. $0.0005 / megapixel of output video. - [Flux Video Upscale](https://doitong.com/developers/models/blackforestlabs/flux-video-upscale.md): `blackforestlabs/flux-video-upscale`. Upscales an MP4 clip by 1.5x to 3x, faithful or with creative detail. from $0.084 / second of input video. - [Flux Vision Upscaler](https://doitong.com/developers/models/flux-vision-upscaler.md): `flux-vision-upscaler`. Image upscaler with a 1-4x factor and a creativity control for how far results may drift from the source. $0.10 / megapixel of output image. - Kandinsky 6.0 VSR (Sber AI), from $0.001: - [Kandinsky 6.0 VSR](https://doitong.com/developers/models/kandinsky6-vsr.md): `kandinsky6-vsr`. from $0.00036 / megapixel of output video. - [Kandinsky 6.0 VSR · Lite](https://doitong.com/developers/models/kandinsky6-vsr/lite.md): `kandinsky6-vsr/lite`. from $0.00036 / megapixel of output video. - Recraft Upscale (Recraft), from $0.004: - [Recraft Creative Upscale](https://doitong.com/developers/models/recraft/upscale/creative.md): `recraft/upscale/creative`. $0.25 / image. - [Recraft Crisp Upscale](https://doitong.com/developers/models/recraft/upscale/crisp.md): `recraft/upscale/crisp`. $0.004 / image. - [SeedVR2 · Image · Seamless](https://doitong.com/developers/models/seedvr/upscale/image/seamless.md): `seedvr/upscale/image/seamless`. Image upscaler that keeps tiling patterns continuous, scaling by a factor up to 10 or to a target resolution. $0.0025 / megapixel of output image. - SeedVR2 (ByteDance), from $0.001: - [SeedVR2 · Image](https://doitong.com/developers/models/seedvr/upscale/image.md): `seedvr/upscale/image`. $0.001 / megapixel of output image. - [SeedVR2 · Video](https://doitong.com/developers/models/seedvr/upscale/video.md): `seedvr/upscale/video`. $0.001 / megapixel of output video. - [Upscale Images](https://doitong.com/developers/models/esrgan.md): `esrgan`. Upscales an image by a factor of 1 to 8 with selectable Real-ESRGAN models and optional face mode. $0.000575 / second of processing time (charged by usage, up to $0.518 per run for the example input; the rest is refunded). - [Video Upscaler](https://doitong.com/developers/models/video-upscaler.md): `video-upscaler`. Upscales a video frame by frame with RealESRGAN, with a scale factor of 1 to 8. $0.0008 / megapixel of output video. ## Models: Background Removal (19) - [Ideogram Remove Background](https://doitong.com/developers/models/ideogram/remove-background.md): `ideogram/remove-background`. Removes an image background and returns the subject on transparency. $0.01 / image. - Bria (Bria AI), from $0.03: - [Bria Guided Remove Background](https://doitong.com/developers/models/bria/guided-remove-background.md): `bria/guided-remove-background`. $0.03 / image. - [Video · Background Removal](https://doitong.com/developers/models/bria/video/background-removal.md): `bria/video/background-removal`. $0.14 / second of input video. - Pixelcut (Pixelcut), from $0.016: - [Pixelcut Background Remover](https://doitong.com/developers/models/pixelcut/background-removal.md): `pixelcut/background-removal`. $0.016 / image. - [Pixelcut Video Background Removal](https://doitong.com/developers/models/pixelcut/video-background-removal.md): `pixelcut/video-background-removal`. $0.022 / 30 frames of input video. - BiRefNet (BiRefNet), from $0.002: - [Birefnet Background Removal](https://doitong.com/developers/models/birefnet.md): `birefnet`. $0.002 / run (estimated per run). - [BiRefNet V2 Background Removal](https://doitong.com/developers/models/birefnet/v2.md): `birefnet/v2`. $0.002 / run (estimated per run). - Bria Rmbg (Bria AI), from $0.018: - [Bria RMBG 2.0](https://doitong.com/developers/models/bria/background/remove.md): `bria/background/remove`. from $0.018 / request. - [Bria's VRMBG 3.0](https://doitong.com/developers/models/bria/video/background-removal/v3.md): `bria/video/background-removal/v3`. $0.05 / second of input video. - [Video · Background Removal · Green Screen Despill](https://doitong.com/developers/models/bria/video/background-removal/green-screen-despill.md): `bria/video/background-removal/green-screen-despill`. $0.05 / second of input video. - Ben v2 (Open model), from $0.001: - [ben-v2-image](https://doitong.com/developers/models/ben/v2/image.md): `ben/v2/image`. $0.102 / run (estimated per run). - [Ben-Video-Bg-Rm](https://doitong.com/developers/models/ben/v2/video.md): `ben/v2/video`. $0.001 / megapixel of input video. - [Birefnet](https://doitong.com/developers/models/birefnet/v2/video.md): `birefnet/v2/video`. Removes backgrounds from video, with six model choices, matting, and mp4, webm, mov or gif output. $0.000575 / second of processing time (charged by usage, up to $2.07 per run for the example input; the rest is refunded). - [Feynobg Background Remover](https://doitong.com/developers/models/feynobg.md): `feynobg`. Removes the background from a single image and returns it with a transparent alpha channel. $0.001 / request. - [Rembg Enhance (Remove Background Enhance)](https://doitong.com/developers/models/smoretalk-ai/rembg-enhance.md): `smoretalk-ai/rembg-enhance`. Removes image backgrounds using matting, suited to vector art, 3D renders and photos. $0.006 / request. - Video Background Removal (VEED), from $0.008: - [Video Background Removal](https://doitong.com/developers/models/veed/video-background-removal.md): `veed/video-background-removal`. from $0.015 / 30 frames of input video. - [Video Background Removal · Fast](https://doitong.com/developers/models/veed/video-background-removal/fast.md): `veed/video-background-removal/fast`. from $0.008 / 30 frames of input video. - [Video Background Removal · Green Screen](https://doitong.com/developers/models/veed/video-background-removal/green-screen.md): `veed/video-background-removal/green-screen`. $0.025 / 30 frames of input video. - [Remove Background](https://doitong.com/developers/models/imageutils/rembg.md): `imageutils/rembg`. Removes the background from an image, with optional cropping to the subject's bounding box. $0.003 / run (estimated per run). ## Models: Text to Speech (60) - [Kling TTS](https://doitong.com/developers/models/kling-video/v1/tts.md): `kling-video/v1/tts`. Text-to-speech with a selectable voice list and speaking rate from 0.8 to 2. $0.007 / request. - ElevenLabs v4 (ElevenLabs), from $0.04: - [Eleven v4 Text to Speech](https://doitong.com/developers/models/elevenlabs/tts/eleven-v4.md): `elevenlabs/tts/eleven-v4`. $0.08 / 1000 characters. - [Eleven v4 Turbo](https://doitong.com/developers/models/elevenlabs/tts/eleven-v4-turbo.md): `elevenlabs/tts/eleven-v4-turbo`. $0.04 / 1000 characters. - [Elevenlabs Tts Eleven V3](https://doitong.com/developers/models/elevenlabs/tts/eleven-v3.md): `elevenlabs/tts/eleven-v3`. $0.10 / 1000 characters. - MiniMax Speech (MiniMax), from $0.06: - [MiniMax Speech 2.6 \[HD\]](https://doitong.com/developers/models/minimax/speech-2.6-hd.md): `minimax/speech-2.6-hd`. $0.10 / 1000 characters. - [MiniMax Speech 2.6 \[Turbo\]](https://doitong.com/developers/models/minimax/speech-2.6-turbo.md): `minimax/speech-2.6-turbo`. $0.06 / 1000 characters. - [MiniMax Speech 2.8 \[Turbo\]](https://doitong.com/developers/models/minimax/speech-2.8-turbo.md): `minimax/speech-2.8-turbo`. $0.06 / 1000 characters. - [MiniMax Speech 2.8 HD](https://doitong.com/developers/models/minimax/speech-2.8-hd.md): `minimax/speech-2.8-hd`. $0.10 / 1000 characters. - [MiniMax Speech-02 HD](https://doitong.com/developers/models/minimax/speech-02-hd.md): `minimax/speech-02-hd`. $0.10 / 1000 characters. - [MiniMax Speech-02 Turbo](https://doitong.com/developers/models/minimax/speech-02-turbo.md): `minimax/speech-02-turbo`. $0.06 / 1000 characters. - [MiniMax Voice Cloning](https://doitong.com/developers/models/minimax/voice-clone.md): `minimax/voice-clone`. $1.5198 / run. - [MiniMax Voice Design](https://doitong.com/developers/models/minimax/voice-design.md): `minimax/voice-design`. $3.00 / run. - [Async Text to Speech Pro V1.0](https://doitong.com/developers/models/async/tts-pro/v1.0.md): `async/tts-pro/v1.0`. Text-to-speech with voice selection, optional voice cloning and six forced-language options. $0.01 / 1000 characters. - [Bytedance Seed Speech Text to Speech](https://doitong.com/developers/models/bytedance/seed-speech/tts/v2.md): `bytedance/seed-speech/tts/v2`. Text-to-speech with many preset voices, speed, pitch and volume control, and spoken-style instructions. $0.03 / 1000 characters. - Chatterbox (Resemble AI), from $0.015: - [Chatterbox · Speech to Speech](https://doitong.com/developers/models/chatterbox/speech-to-speech.md): `chatterbox/speech-to-speech`. $0.015 / minute of input audio. - [Chatterbox · Text to Speech](https://doitong.com/developers/models/chatterbox/text-to-speech.md): `chatterbox/text-to-speech`. $0.025 / 1000 characters. - [Chatterbox · Text to Speech · Multilingual](https://doitong.com/developers/models/chatterbox/text-to-speech/multilingual.md): `chatterbox/text-to-speech/multilingual`. Multilingual text-to-speech covering 23 languages, limited to 300 characters per request. $0.025 / 1000 characters. - Chatterboxhd (Resemble AI), from $0.011: - [Chatterboxhd · Speech to Speech](https://doitong.com/developers/models/resemble-ai/chatterboxhd/speech-to-speech.md): `resemble-ai/chatterboxhd/speech-to-speech`. $0.02 / minute of input audio. - [Chatterboxhd · Text to Speech](https://doitong.com/developers/models/resemble-ai/chatterboxhd/text-to-speech.md): `resemble-ai/chatterboxhd/text-to-speech`. $0.0108 / run. - [CSM-1B](https://doitong.com/developers/models/csm-1b.md): `csm-1b`. Conversational text-to-speech model that takes a scene of lines plus optional audio context. $0.03 / run (estimated per run). - Dia TTS (Nari Labs), from $0.04: - [Dia](https://doitong.com/developers/models/dia-tts.md): `dia-tts`. $0.04 / 1000 characters. - [Dia Tts](https://doitong.com/developers/models/dia-tts/voice-clone.md): `dia-tts/voice-clone`. $0.04 / 1000 characters. - ElevenLabs Audio (ElevenLabs), from $0.05: - [ElevenLabs TTS Multilingual v2](https://doitong.com/developers/models/elevenlabs/tts/multilingual-v2.md): `elevenlabs/tts/multilingual-v2`. $0.10 / 1000 characters. - [ElevenLabs TTS Turbo v2.5](https://doitong.com/developers/models/elevenlabs/tts/turbo-v2.5.md): `elevenlabs/tts/turbo-v2.5`. $0.05 / 1000 characters. - [Elevenlabs](https://doitong.com/developers/models/elevenlabs/text-to-dialogue/eleven-v3.md): `elevenlabs/text-to-dialogue/eleven-v3`. Turns a list of text and voice ID pairs into a multi-speaker dialogue audio track. $0.10 / run (estimated per run). - [F5 TTS](https://doitong.com/developers/models/f5-tts.md): `f5-tts`. Voice-cloning speech synthesis from a reference audio clip, using F5-TTS or E2-TTS. $0.05 / 1000 characters. - [Gemini 3.1 Flash Tts](https://doitong.com/developers/models/gemini-3.1-flash-tts.md): `gemini-3.1-flash-tts`. Gemini 3.1 Flash text-to-speech with inline style control, 30 voices and up to 10 speakers. $0.05 / 1000 characters. - Gemini 3.8 Flash (Google), from $0.045: - [Gemini 3.8 Flash Lite TTS](https://doitong.com/developers/models/google/gemini-3.8-flash-lite-tts.md): `google/gemini-3.8-flash-lite-tts`. $0.111 / run (estimated per run). - [Gemini 3.8 Flash TTS](https://doitong.com/developers/models/google/gemini-3.8-flash-tts.md): `google/gemini-3.8-flash-tts`. $0.045 / run (estimated per run). - [Gemini TTS](https://doitong.com/developers/models/gemini-tts.md): `gemini-tts`. Text-to-speech with 30 voices, multi-speaker dialogue, style instructions and a Flash or Pro model choice. $0.03 / run (estimated per run). - [Index TTS 2.0](https://doitong.com/developers/models/index-tts-2/text-to-speech.md): `index-tts-2/text-to-speech`. Speech synthesis from a reference voice clip and text, with emotion control via audio, prompt or per-emotion strengths. $0.002 / second of generated audio (charged by usage, up to $0.06 per run for the example input; the rest is refunded). - [Inworld TTS-1.5 Max](https://doitong.com/developers/models/inworld-tts.md): `inworld-tts`. Text-to-speech with a large catalog of named English and other voices and selectable sample rates. $0.01 / 1000 characters. - Kokoro TTS (Hexgrad), from $0.02: - [Kokoro TTS](https://doitong.com/developers/models/kokoro/american-english.md): `kokoro/american-english`. $0.02 / 1000 characters. - [Kokoro TTS (Brazilian Portuguese)](https://doitong.com/developers/models/kokoro/brazilian-portuguese.md): `kokoro/brazilian-portuguese`. $0.02 / 1000 characters. - [Kokoro TTS (British English)](https://doitong.com/developers/models/kokoro/british-english.md): `kokoro/british-english`. $0.02 / 1000 characters. - [Kokoro TTS (French)](https://doitong.com/developers/models/kokoro/french.md): `kokoro/french`. $0.02 / 1000 characters. - [Kokoro TTS (Hindi)](https://doitong.com/developers/models/kokoro/hindi.md): `kokoro/hindi`. $0.02 / 1000 characters. - [Kokoro TTS (Italian)](https://doitong.com/developers/models/kokoro/italian.md): `kokoro/italian`. $0.02 / 1000 characters. - [Kokoro TTS (Japanese)](https://doitong.com/developers/models/kokoro/japanese.md): `kokoro/japanese`. $0.02 / 1000 characters. - [Kokoro TTS (Mandarin Chinese)](https://doitong.com/developers/models/kokoro/mandarin-chinese.md): `kokoro/mandarin-chinese`. $0.02 / 1000 characters. - [Kokoro TTS (Spanish)](https://doitong.com/developers/models/kokoro/spanish.md): `kokoro/spanish`. $0.02 / 1000 characters. - [Kotoba Text-to-Speech](https://doitong.com/developers/models/kotoba-technologies/kotoba-tts/v2/tts/ws.md): `kotoba-technologies/kotoba-tts/v2/tts/ws`. Japanese text-to-speech streamed as it is generated, with two voices and WAV output. $0.045 / 1000 characters. - Maya (Maya Research), from $0.049: - [Maya · Batch](https://doitong.com/developers/models/maya/batch.md): `maya/batch`. $0.049 / run (estimated per run). - [Maya · Stream](https://doitong.com/developers/models/maya/stream.md): `maya/stream`. $0.049 / run (estimated per run). - [Maya1](https://doitong.com/developers/models/maya.md): `maya`. $0.049 / run (estimated per run). - MiniMax Preview (MiniMax), from $0.06: - [Minimax · Preview · Speech 2.5 HD](https://doitong.com/developers/models/minimax/preview/speech-2.5-hd.md): `minimax/preview/speech-2.5-hd`. $0.10 / 1000 characters. - [Minimax · Preview · Speech 2.5 Turbo](https://doitong.com/developers/models/minimax/preview/speech-2.5-turbo.md): `minimax/preview/speech-2.5-turbo`. $0.06 / 1000 characters. - [Orpheus TTS](https://doitong.com/developers/models/orpheus-tts.md): `orpheus-tts`. Text-to-speech with eight named voices and inline emotive tags such as laugh and sigh. $0.05 / 1000 characters. - Tada (Open model), from $0.05: - [Tada](https://doitong.com/developers/models/tada/3b/text-to-speech.md): `tada/3b/text-to-speech`. $0.08 / 1000 characters. - [Tada TTS 1B](https://doitong.com/developers/models/tada/1b/text-to-speech.md): `tada/1b/text-to-speech`. $0.05 / 1000 characters. - Vibevoice (Microsoft), from $0.01: - [Vibevoice](https://doitong.com/developers/models/vibevoice/0.5b.md): `vibevoice/0.5b`. $0.01 / run (estimated per run). - [VibeVoice 1.5B](https://doitong.com/developers/models/vibevoice.md): `vibevoice`. $0.02 / run (estimated per run). - [VibeVoice 7B](https://doitong.com/developers/models/vibevoice/7b.md): `vibevoice/7b`. $0.04 / run (estimated per run). - [xAI Text to Speech](https://doitong.com/developers/models/xai/tts/v1.md): `xai/tts/v1`. Text-to-speech with built-in voices, language selection and inline expressive speech tags. $0.015 / 1000 characters. - [Zonos-Audio-Clone](https://doitong.com/developers/models/zonos.md): `zonos`. Voice-cloning speech: speaks your text in the voice of a reference audio clip. $0.05 / 1000 characters. - [Zonos2 Text to Speech](https://doitong.com/developers/models/zonos2.md): `zonos2`. Multilingual voice-cloning TTS with sampling controls and a choice between close match or expressive delivery. $0.01 / minute of generated audio (charged by usage, up to $0.02 per run for the example input; the rest is refunded). - Qwen 3 TTS (Alibaba), from $0.07: - [Qwen 3 TTS - Text to Speech \[0.6B\]](https://doitong.com/developers/models/qwen-3-tts/text-to-speech/0.6b.md): `qwen-3-tts/text-to-speech/0.6b`. $0.07 / 1000 characters. - [Qwen 3 TTS - Text to Speech \[1.7B\]](https://doitong.com/developers/models/qwen-3-tts/text-to-speech/1.7b.md): `qwen-3-tts/text-to-speech/1.7b`. $0.09 / 1000 characters. - [Qwen 3 TTS - Voice Design \[1.7B\]](https://doitong.com/developers/models/qwen-3-tts/voice-design/1.7b.md): `qwen-3-tts/voice-design/1.7b`. $0.09 / 1000 characters. - [Qwen Audio 3.0 TTS (Flash)](https://doitong.com/developers/models/alibaba/qwen-audio-3-tts.md): `alibaba/qwen-audio-3-tts`. Fast multilingual text-to-speech with a choice of named voices and an optional language setting. $0.05 / 1000 characters. ## Models: Speech to Text (14) - [Cohere Transcribe](https://doitong.com/developers/models/cohere-transcribe.md): `cohere-transcribe`. Speech-to-text model with 14 selectable languages and an optional punctuation toggle. $0.0000694 / second of input audio. - ElevenLabs Speech to Text (ElevenLabs), from $0.008: - [ElevenLabs Speech to Text](https://doitong.com/developers/models/elevenlabs/speech-to-text.md): `elevenlabs/speech-to-text`. $0.03 / minute of input audio. - [ElevenLabs Speech to Text - Scribe V2](https://doitong.com/developers/models/elevenlabs/speech-to-text/scribe-v2.md): `elevenlabs/speech-to-text/scribe-v2`. $0.008 / minute of input audio. - [Kotoba Speech-to-Text](https://doitong.com/developers/models/kotoba-technologies/kotoba-stt/v1/speech-to-text.md): `kotoba-technologies/kotoba-stt/v1/speech-to-text`. Speech-to-text for clips up to 2 minutes, tuned for Japanese, with word timestamps and keyword hints. $0.0000694 / second of input audio. - [Nemotron Asr Multilingual](https://doitong.com/developers/models/nvidia/nemotron-asr-multilingual/asr.md): `nvidia/nemotron-asr-multilingual/asr`. Multilingual speech transcription with auto language detection and four speed/accuracy levels. $0.008 / minute of input audio. - [Pipecat's Smart Turn model](https://doitong.com/developers/models/smart-turn.md): `smart-turn`. Audio-based turn detection that predicts whether a speaker's turn is complete or incomplete. $0.00111 / second of processing time (charged by usage, up to $1.998 per run for the example input; the rest is refunded). - [Silero VAD](https://doitong.com/developers/models/silero-vad.md): `silero-vad`. Detects whether audio contains speech and returns speech timestamps, without transcribing. $0.00001 / second of input audio. - Speech To Text (Open model), from $0.001: - [Speech-to-Text](https://doitong.com/developers/models/speech-to-text.md): `speech-to-text`. $0.0008 / second of input audio. - [Speech-To-text · Stream](https://doitong.com/developers/models/speech-to-text/stream.md): `speech-to-text/stream`. $0.0008 / second of input audio. - [Speech-to-Text · Turbo](https://doitong.com/developers/models/speech-to-text/turbo.md): `speech-to-text/turbo`. $0.0008 / second of input audio. - [Speech-to-Text · Turbo · Stream](https://doitong.com/developers/models/speech-to-text/turbo/stream.md): `speech-to-text/turbo/stream`. Turbo transcription that streams partial results, combining the faster variant with incremental output. $0.0008 / second of input audio. - [Wizper (Whisper v3)](https://doitong.com/developers/models/wizper.md): `wizper`. Whisper v3 speech transcription and translation to English with timestamped chunks. $0.00111 / second of processing time (charged by usage, up to $1.998 per run for the example input; the rest is refunded). - [Elevenlabs - Forced Alignment](https://doitong.com/developers/models/elevenlabs/forced-alignment.md): `elevenlabs/forced-alignment`. Aligns a known transcript to an audio recording and returns word and character timing. $0.22 / hour of input audio. - [Nemotron 3 Nano Omni · Audio](https://doitong.com/developers/models/nvidia/nemotron-3-nano-omni/audio.md): `nvidia/nemotron-3-nano-omni/audio`. Answers prompts about an audio clip (wav or mp3, up to 50 minutes), returning text. $0.01 / 1000 tokens (charged by usage, up to $0.622 per run for the example input; the rest is refunded). ## Models: Text to Music (31) - MiniMax Music (MiniMax), from $0.03: - [MiniMax (Hailuo AI) Music](https://doitong.com/developers/models/minimax-music.md): `minimax-music`. $0.035 / request. - [MiniMax (Hailuo AI) Music v1.5](https://doitong.com/developers/models/minimax-music/v1.5.md): `minimax-music/v1.5`. $0.03 / request. - [Minimax Music](https://doitong.com/developers/models/minimax-music/v2.md): `minimax-music/v2`. $0.03 / request. - [Minimax Music 2.5](https://doitong.com/developers/models/minimax-music/v2.5.md): `minimax-music/v2.5`. $0.15 / request. - [Minimax Music 2.6](https://doitong.com/developers/models/minimax-music/v2.6.md): `minimax-music/v2.6`. $0.15 / request. - [MiniMax Music 3](https://doitong.com/developers/models/minimax/music-3.md): `minimax/music-3`. $0.002 / second (60 s ≈ $0.12). - ACE Step (ACE Studio), from $0.001: - [ACE Step](https://doitong.com/developers/models/ace-step.md): `ace-step`. $0.0002 / second (60 s ≈ $0.012). - [ACE Step Audio Inpaint](https://doitong.com/developers/models/ace-step/audio-inpaint.md): `ace-step/audio-inpaint`. $0.0002 / second of input audio. - [ACE Step Audio Outpaint](https://doitong.com/developers/models/ace-step/audio-outpaint.md): `ace-step/audio-outpaint`. $0.0002 / second of output audio. - [ACE Step Audio To Audio](https://doitong.com/developers/models/ace-step/audio-to-audio.md): `ace-step/audio-to-audio`. $0.0002 / second of input audio. - [ACE Step Prompt To Audio](https://doitong.com/developers/models/ace-step/prompt-to-audio.md): `ace-step/prompt-to-audio`. $0.0002 / second (60 s ≈ $0.012). - [music generator](https://doitong.com/developers/models/cassetteai/music-generator.md): `cassetteai/music-generator`. Text-to-music that makes a track of 10 to 180 seconds from a prompt. $0.02 / minute of output audio. - [DiffRhythm: Lyrics to Song](https://doitong.com/developers/models/diffrhythm.md): `diffrhythm`. Turns lyrics into a full song, with optional style prompt, reference audio and 95 s or 285 s length. $0.001 / second (100 s ≈ $0.10). - [Elevenlabs Music](https://doitong.com/developers/models/elevenlabs/music.md): `elevenlabs/music`. Text-to-music generator driven by a prompt or a structured composition plan, with instrumental option. $0.60 / minute of output audio. - Elevenlabs Music (ElevenLabs), from $0.60: - [Elevenlabs Music v2](https://doitong.com/developers/models/elevenlabs/music/v2.md): `elevenlabs/music/v2`. $0.60 / minute of output audio. - [Elevenlabs Music v2.5](https://doitong.com/developers/models/elevenlabs/music/v2.5.md): `elevenlabs/music/v2.5`. $0.60 / minute of output audio. - [Lyria 3.5](https://doitong.com/developers/models/google/lyria-3.5.md): `google/lyria-3.5`. Text-to-music that returns an MP3 and lyrics, with optional image as mood inspiration. $0.10 / request. - [Lyria2](https://doitong.com/developers/models/lyria2.md): `lyria2`. Google text-to-music model that composes a track from a prompt with a negative prompt option. $0.10 / run (estimated per run). - Lyria3 (Google), from $0.04: - [Lyria 3 Pro](https://doitong.com/developers/models/lyria3/pro.md): `lyria3/pro`. $0.08 / request. - [Lyria3](https://doitong.com/developers/models/lyria3.md): `lyria3`. $0.04 / request. - Mureka 9.5 (Mureka), from $0.045: - [Mureka 9.5 Instrumental Generation](https://doitong.com/developers/models/mureka/api/generate/instrumental.md): `mureka/api/generate/instrumental`. from $0.045 / request. - [Mureka 9.5 Song Generation](https://doitong.com/developers/models/mureka/api/generate/song.md): `mureka/api/generate/song`. from $0.45 / run. - [Sonilo V1.1 Text to Music](https://doitong.com/developers/models/sonilo/v1.1/text-to-music.md): `sonilo/v1.1/text-to-music`. Text-to-music that returns up to 3 tracks per request and durations up to 600 seconds. $0.0025 / second of output audio. - Stable Audio 3 (Stability AI), from $0.022: - [Stable Audio 3 Small Music Audio Inpainting](https://doitong.com/developers/models/stable-audio-3/small/music/audio-inpainting.md): `stable-audio-3/small/music/audio-inpainting`. $0.026 / request. - [Stable Audio 3 Small Music Audio Outpainting](https://doitong.com/developers/models/stable-audio-3/small/music/audio-outpainting.md): `stable-audio-3/small/music/audio-outpainting`. $0.0265 / request. - [Stable Audio 3 Small Music Base Audio Inpainting](https://doitong.com/developers/models/stable-audio-3/small/music/base/audio-inpainting.md): `stable-audio-3/small/music/base/audio-inpainting`. $0.0333 / request. - [Stable Audio 3 Small Music Base Audio Outpainting](https://doitong.com/developers/models/stable-audio-3/small/music/base/audio-outpainting.md): `stable-audio-3/small/music/base/audio-outpainting`. $0.0339 / request. - [Stable Audio 3 Small Music Base Audio to Audio](https://doitong.com/developers/models/stable-audio-3/small/music/base/audio-to-audio.md): `stable-audio-3/small/music/base/audio-to-audio`. $0.032 / request. - [Stable Audio 3 Small Music Text to Audio](https://doitong.com/developers/models/stable-audio-3/small/music/text-to-audio.md): `stable-audio-3/small/music/text-to-audio`. $0.0217 / request. - [Stable Audio 3 · Small · Music · Audio to Audio](https://doitong.com/developers/models/stable-audio-3/small/music/audio-to-audio.md): `stable-audio-3/small/music/audio-to-audio`. $0.0248 / request. - [Stable Audio 3 · Small · Music · Base · Text to Audio](https://doitong.com/developers/models/stable-audio-3/small/music/base/text-to-audio.md): `stable-audio-3/small/music/base/text-to-audio`. $0.0281 / request. ## Models: Audio (48) - [FFmpeg API \[Merge Audios\]](https://doitong.com/developers/models/ffmpeg-api/merge-audios.md): `ffmpeg-api/merge-audios`. Concatenates 2 to 5 audio files in order into one file, with a selectable output codec and rate. $0.00017 / second of processing time (charged by usage, up to $0.306 per run for the example input; the rest is refunded). - LTX 2.3 Quality (Lightricks), from $0.682: - [Ltx 2.3 Quality · Text to Audio](https://doitong.com/developers/models/ltx-2.3-quality/text-to-audio.md): `ltx-2.3-quality/text-to-audio`. from $0.682 / run (estimated per run). - [Ltx 2.3 Quality · Text to Audio · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/text-to-audio/lora.md): `ltx-2.3-quality/text-to-audio/lora`. from $0.70 / run (estimated per run). - Workflow Utilities (Utility), from $0.001: - [Workflow Utilities Audio Compressor](https://doitong.com/developers/models/workflow-utilities/audio-compressor.md): `workflow-utilities/audio-compressor`. $0.001 / second of processing time (charged by usage, up to $1.80 per run for the example input; the rest is refunded). - [Workflow Utilities Impulse Response](https://doitong.com/developers/models/workflow-utilities/impulse-response.md): `workflow-utilities/impulse-response`. $0.001 / second of processing time (charged by usage, up to $1.80 per run for the example input; the rest is refunded). - [VEED Clean Audio](https://doitong.com/developers/models/veed/clean-audio.md): `veed/clean-audio`. Speech denoiser that cleans noisy recordings or a video's audio track and normalizes loudness. $0.0125 / minute of input audio. - ElevenLabs Audio (ElevenLabs), from $0.001: - [ElevenLabs Audio Isolation](https://doitong.com/developers/models/elevenlabs/audio-isolation.md): `elevenlabs/audio-isolation`. $0.10 / minute of input file. - [Elevenlabs Sound Effects V2](https://doitong.com/developers/models/elevenlabs/sound-effects/v2.md): `elevenlabs/sound-effects/v2`. $0.002 / second (0.5 s ≈ $0.001). - [Sound Effects Generator](https://doitong.com/developers/models/cassetteai/sound-effects-generator.md): `cassetteai/sound-effects-generator`. Text-to-sound-effect generator for clips of 1 to 30 seconds. $0.01 / request. - [ElevenLabs Voice Changer](https://doitong.com/developers/models/elevenlabs/voice-changer.md): `elevenlabs/voice-changer`. Converts the voice in an existing recording to a chosen voice, with optional background noise removal. $0.30 / minute of input audio. - [Mureka 9.5 Podcast Generation](https://doitong.com/developers/models/mureka/api/generate/podcast.md): `mureka/api/generate/podcast`. Generates podcast audio from an ordered list of conversation turns with per-turn voices. $0.019 / run (estimated per run). - [Sonilo V1.1 Text to Sound Effects](https://doitong.com/developers/models/sonilo/v1.1/text-to-sound-effects.md): `sonilo/v1.1/text-to-sound-effects`. Creates sound effects from a text description, 0.5 to 180 seconds, in WAV, MP3, AAC or FLAC. $0.0018 / second of output audio. - MMAudio V2 (Sony AI), from $0.008: - [MMAudio V2](https://doitong.com/developers/models/mmaudio-v2.md): `mmaudio-v2`. $0.001 / second (8 s ≈ $0.008). - [MMAudio V2 Text to Audio](https://doitong.com/developers/models/mmaudio-v2/text-to-audio.md): `mmaudio-v2/text-to-audio`. $0.001 / second (8 s ≈ $0.008). - [DeepFilterNet 3](https://doitong.com/developers/models/deepfilternet3.md): `deepfilternet3`. Speech enhancer that strips background noise from an audio file and returns it in a chosen format and bitrate. $0.001 / second of input audio. - [Demucs](https://doitong.com/developers/models/demucs.md): `demucs`. Splits a music track into separate stems such as vocals, drums, bass, guitar and piano, with selectable variants. $0.0007 / second of input audio. - [Ffmpeg Api · Loudnorm](https://doitong.com/developers/models/ffmpeg-api/loudnorm.md): `ffmpeg-api/loudnorm`. Normalizes audio loudness to an EBU R128 target with adjustable LUFS, true peak and range settings. $0.00017 / second of processing time (charged by usage, up to $0.306 per run for the example input; the rest is refunded). - Grok Voice (xAI), from $0.006: - [Grok Voice](https://doitong.com/developers/models/xai/grok-voice.md): `xai/grok-voice`. $0.00083 / second of the voice session (charged by usage, up to $1.494 per run for the example input; the rest is refunded). - [Grok Voice · Realtime](https://doitong.com/developers/models/xai/grok-voice/realtime.md): `xai/grok-voice/realtime`. $0.00083 / second of the voice session (charged by usage, up to $1.494 per run for the example input; the rest is refunded). - [Kling Video Create Voice](https://doitong.com/developers/models/kling-video/create-voice.md): `kling-video/create-voice`. Registers a custom voice from a 5-30 s audio or video sample and returns a voice ID. $0.007 / request. - [Mirelo SFX2.0 · Text to Audio](https://doitong.com/developers/models/mirelo-ai/sfx2.0/text-to-audio.md): `mirelo-ai/sfx2.0/text-to-audio`. Sound effects from a text description, with negative prompt, duration and several samples. $0.01 / second of output audio. - Personaplex (NVIDIA), from $0.001: - [Personaplex](https://doitong.com/developers/models/personaplex.md): `personaplex`. $0.001 / second of input audio. - [Personaplex · Realtime](https://doitong.com/developers/models/personaplex/realtime.md): `personaplex/realtime`. $0.001 / second of processing time (charged by usage, up to $1.80 per run for the example input; the rest is refunded). - Qwen 3 TTS (Alibaba), from $0.001: - [Qwen 3 TTS - Clone Voice \[0.6B\]](https://doitong.com/developers/models/qwen-3-tts/clone-voice/0.6b.md): `qwen-3-tts/clone-voice/0.6b`. $0.0007 / minute of input audio. - [Qwen 3 TTS - Clone Voice \[1.7B\]](https://doitong.com/developers/models/qwen-3-tts/clone-voice/1.7b.md): `qwen-3-tts/clone-voice/1.7b`. $0.0008 / minute of input audio. - Sam Audio (Meta), from $0.05: - [Sam Audio · Separate](https://doitong.com/developers/models/sam-audio/separate.md): `sam-audio/separate`. from $0.05 / 30 seconds of input audio. - [Sam Audio · Span Separate](https://doitong.com/developers/models/sam-audio/span-separate.md): `sam-audio/span-separate`. from $0.05 / 30 seconds of input audio. - [Seed Audio 1.0](https://doitong.com/developers/models/bytedance/seed-audio-1.0.md): `bytedance/seed-audio-1.0`. Speech and audio generator driven by text, up to 3 reference audio clips or one image, with pitch and speed controls. $0.1875 / minute of generated audio (charged by usage, up to $0.154 per run for the example input; the rest is refunded). - Stable Audio (Stability AI), from $0.20: - [Stable Audio 2.5 · Audio to Audio](https://doitong.com/developers/models/stable-audio-25/audio-to-audio.md): `stable-audio-25/audio-to-audio`. $0.20 / request. - [Stable Audio 2.5 · Text to Audio](https://doitong.com/developers/models/stable-audio-25/text-to-audio.md): `stable-audio-25/text-to-audio`. $0.20 / request. - [Stable Audio 25](https://doitong.com/developers/models/stable-audio-25/inpaint.md): `stable-audio-25/inpaint`. $0.20 / request. - Stable Audio 3 (Stability AI), from $0.021: - [Stable Audio 3 Medium Audio Inpainting](https://doitong.com/developers/models/stable-audio-3/medium/audio-inpainting.md): `stable-audio-3/medium/audio-inpainting`. $0.0442 / request. - [Stable Audio 3 Medium Audio Outpainting](https://doitong.com/developers/models/stable-audio-3/medium/audio-outpainting.md): `stable-audio-3/medium/audio-outpainting`. $0.0446 / request. - [Stable Audio 3 Medium Audio to Audio](https://doitong.com/developers/models/stable-audio-3/medium/audio-to-audio.md): `stable-audio-3/medium/audio-to-audio`. $0.0417 / request. - [Stable Audio 3 Medium Base Audio Inpainting](https://doitong.com/developers/models/stable-audio-3/medium/base/audio-inpainting.md): `stable-audio-3/medium/base/audio-inpainting`. $0.0537 / request. - [Stable Audio 3 Medium Base Audio Outpainting](https://doitong.com/developers/models/stable-audio-3/medium/base/audio-outpainting.md): `stable-audio-3/medium/base/audio-outpainting`. $0.0554 / request. - [Stable Audio 3 Medium Base Audio to Audio](https://doitong.com/developers/models/stable-audio-3/medium/base/audio-to-audio.md): `stable-audio-3/medium/base/audio-to-audio`. $0.0523 / request. - [Stable Audio 3 Medium Base Text to Audio](https://doitong.com/developers/models/stable-audio-3/medium/base/text-to-audio.md): `stable-audio-3/medium/base/text-to-audio`. $0.0479 / request. - [Stable Audio 3 Small SFX Audio Inpainting](https://doitong.com/developers/models/stable-audio-3/small/sfx/audio-inpainting.md): `stable-audio-3/small/sfx/audio-inpainting`. $0.0259 / request. - [Stable Audio 3 Small SFX Audio Outpainting](https://doitong.com/developers/models/stable-audio-3/small/sfx/audio-outpainting.md): `stable-audio-3/small/sfx/audio-outpainting`. $0.0271 / request. - [Stable Audio 3 Small SFX Base Audio Inpainting](https://doitong.com/developers/models/stable-audio-3/small/sfx/base/audio-inpainting.md): `stable-audio-3/small/sfx/base/audio-inpainting`. $0.0331 / request. - [Stable Audio 3 Small SFX Base Audio Outpainting](https://doitong.com/developers/models/stable-audio-3/small/sfx/base/audio-outpainting.md): `stable-audio-3/small/sfx/base/audio-outpainting`. $0.0337 / request. - [Stable Audio 3 Small SFX Base Audio to Audio](https://doitong.com/developers/models/stable-audio-3/small/sfx/base/audio-to-audio.md): `stable-audio-3/small/sfx/base/audio-to-audio`. $0.0315 / request. - [Stable Audio 3 Small SFX Base Text to Audio](https://doitong.com/developers/models/stable-audio-3/small/sfx/base/text-to-audio.md): `stable-audio-3/small/sfx/base/text-to-audio`. $0.0283 / request. - [Stable Audio 3 Small SFX Text to Audio](https://doitong.com/developers/models/stable-audio-3/small/sfx/text-to-audio.md): `stable-audio-3/small/sfx/text-to-audio`. $0.0206 / request. - [Stable Audio 3 · Medium · Text to Audio](https://doitong.com/developers/models/stable-audio-3/medium/text-to-audio.md): `stable-audio-3/medium/text-to-audio`. $0.0376 / request. - [Stable Audio 3 · Small · SFX · Audio to Audio](https://doitong.com/developers/models/stable-audio-3/small/sfx/audio-to-audio.md): `stable-audio-3/small/sfx/audio-to-audio`. $0.024 / request. - [Stable Audio Open](https://doitong.com/developers/models/stable-audio.md): `stable-audio`. Open text-to-audio model that creates clips up to 47 seconds, suited to short music and sounds. $0.02 / run (estimated per run). ## Models: Video to Audio (11) - [PixVerse Sound Effects](https://doitong.com/developers/models/pixverse/sound-effects.md): `pixverse/sound-effects`. Adds generated sound effects and music to an existing video from an optional text description. $0.10 / 5 seconds of input video. - [Video Sound Effects Generator](https://doitong.com/developers/models/cassetteai/video-sound-effects-generator.md): `cassetteai/video-sound-effects-generator`. Analyzes a video and adds a generated sound-effects track, returning the re-sounded video. $0.20 / minute of input video. - Sonilo V1.1 (Sonilo), from $0.009: - [Sonilo V1.1](https://doitong.com/developers/models/sonilo/v1.1/video-to-music.md): `sonilo/v1.1/video-to-music`. $0.009 / second of output audio. - [Sonilo V1.1 Video to Sound Effects](https://doitong.com/developers/models/sonilo/v1.1/video-to-sound-effects.md): `sonilo/v1.1/video-to-sound-effects`. $0.009 / second of input video. - [Sonilo V1.1 Video to Video Sound Effects](https://doitong.com/developers/models/sonilo/v1.1/video-to-video-sound-effects.md): `sonilo/v1.1/video-to-video-sound-effects`. $0.009 / second of input video. - [Kling Video · Video to Audio](https://doitong.com/developers/models/kling-video/video-to-audio.md): `kling-video/video-to-audio`. Generates sound effects and background music for a 3-20 s video and returns audio plus dubbed video. $0.035 / video. - [Mirelo SFX2.0 · Video to Audio](https://doitong.com/developers/models/mirelo-ai/sfx2.0/video-to-audio.md): `mirelo-ai/sfx2.0/video-to-audio`. Creates a soundtrack for an input video and returns it as separate audio files. $0.01 / second of output audio. - [Sam Audio · Visual Separate](https://doitong.com/developers/models/sam-audio/visual-separate.md): `sam-audio/visual-separate`. Separates a sound from a video's audio track, guided by an optional mask video and text prompt. from $0.05 / 30 seconds of input video. - [Hunyuan Video Foley](https://doitong.com/developers/models/hunyuan-video-foley.md): `hunyuan-video-foley`. Adds generated sound effects to an existing video from a text description. $0.10 / 10 seconds of input video. - Thinksound (Open model), from $0.228: - [ThinkSound](https://doitong.com/developers/models/thinksound.md): `thinksound`. $0.001 / second of processing time (charged by usage, up to $3.60 per run for the example input; the rest is refunded). - [ThinkSound · Audio](https://doitong.com/developers/models/thinksound/audio.md): `thinksound/audio`. $0.001 / second of processing time (charged by usage, up to $1.80 per run for the example input; the rest is refunded). ## Models: Image to 3D (41) - [Hunyuan World · Image to World](https://doitong.com/developers/models/hunyuan_world/image-to-world.md): `hunyuan_world/image-to-world`. Turns one image into a 3D world file, guided by foreground labels and classes. $0.30 / request. - Sam3 (Meta), from $0.02: - [Sam 3 · 3D Body](https://doitong.com/developers/models/sam-3/3d-body.md): `sam-3/3d-body`. $0.02 / run (estimated per run). - [Sam 3 · 3D Objects](https://doitong.com/developers/models/sam-3/3d-objects.md): `sam-3/3d-objects`. $0.02 / run (estimated per run). - Hi3D (Hitem3D), from $1.80: - [Hi3D Image to 3D · v3.0](https://doitong.com/developers/models/hitem3d/hi3d/v3.0/image-to-3d.md): `hitem3d/hi3d/v3.0/image-to-3d`. from $1.80 / run. - [Hi3D Multiview to 3D · v3.0 · Multi View to 3D](https://doitong.com/developers/models/hitem3d/hi3d/v3.0/multi-view-to-3d.md): `hitem3d/hi3d/v3.0/multi-view-to-3d`. from $1.80 / run. - Hunyuan3D (Tencent), from $0.08: - [Hunyuan3D](https://doitong.com/developers/models/hunyuan3d/v2.md): `hunyuan3d/v2`. from $0.16 / request. - [Hunyuan3D · Mini](https://doitong.com/developers/models/hunyuan3d/v2/mini.md): `hunyuan3d/v2/mini`. from $0.10 / request. - [Hunyuan3D · Mini · Turbo](https://doitong.com/developers/models/hunyuan3d/v2/mini/turbo.md): `hunyuan3d/v2/mini/turbo`. $0.08 / request. - [Hunyuan3D · Multi View](https://doitong.com/developers/models/hunyuan3d/v2/multi-view.md): `hunyuan3d/v2/multi-view`. from $0.16 / request. - [Hunyuan3D · Multi View · Turbo](https://doitong.com/developers/models/hunyuan3d/v2/multi-view/turbo.md): `hunyuan3d/v2/multi-view/turbo`. from $0.14 / request. - [Hunyuan3D · Turbo](https://doitong.com/developers/models/hunyuan3d/v2/turbo.md): `hunyuan3d/v2/turbo`. from $0.14 / request. - [Hyper3d](https://doitong.com/developers/models/hyper3d/rodin/v2.md): `hyper3d/rodin/v2`. Rodin v2 text or image to 3D with up to 5 input images, quad or triangle mesh presets and preview render. $0.40 / request. - Hyper3D - Rodin V2.5 (Hyper3D), from $0.10: - [Hyper3D - Rodin V2.5 - Image to 3D](https://doitong.com/developers/models/hyper3d/rodin/v2.5.md): `hyper3d/rodin/v2.5`. from $0.40 / request. - [Hyper3D - Rodin V2.5 - Image to 3D - Fast](https://doitong.com/developers/models/hyper3d/rodin/v2.5/fast.md): `hyper3d/rodin/v2.5/fast`. $0.10 / request. - [Hyper3D Rodin](https://doitong.com/developers/models/hyper3d/rodin.md): `hyper3d/rodin`. Rodin 3D generation from text or images with PBR or shaded materials and quality tiers. $0.40 / request. - [Pixal3d](https://doitong.com/developers/models/pixal3d.md): `pixal3d`. Converts a single image into a textured GLB 3D model with detailed control over each generation stage. from $0.30 / request. - [ReconViaGen 0.5](https://doitong.com/developers/models/reconviagen-0.5.md): `reconviagen-0.5`. Multi-view image-to-3D reconstruction that outputs a textured GLB mesh from 1 to 16 photos of one object. from $0.25 / request. - Trellis (Microsoft), from $0.02: - [Trellis](https://doitong.com/developers/models/trellis.md): `trellis`. $0.02 / request. - [Trellis · Multi](https://doitong.com/developers/models/trellis/multi.md): `trellis/multi`. $0.02 / request. - Trellis 2 (Microsoft), from $0.20: - [Trellis 2](https://doitong.com/developers/models/trellis-2.md): `trellis-2`. from $0.25 / request. - [Trellis 2 · Retexture](https://doitong.com/developers/models/trellis-2/retexture.md): `trellis-2/retexture`. from $0.20 / request. - [TRELLIS.2 LoRA Inference](https://doitong.com/developers/models/trellis-2-lora.md): `trellis-2-lora`. Trellis 2 image-to-3D that can apply custom LoRA adapters for structure, geometry and texture. from $0.25 / request. - Tripo3d (Tripo), from $0.05: - [Tripo3D · Image to 3D](https://doitong.com/developers/models/tripo3d/tripo/v2.5/image-to-3d.md): `tripo3d/tripo/v2.5/image-to-3d`. from $0.20 / run. - [Tripo3D · Multiview to 3D](https://doitong.com/developers/models/tripo3d/tripo/v2.5/multiview-to-3d.md): `tripo3d/tripo/v2.5/multiview-to-3d`. from $0.20 / run. - [Triposplat](https://doitong.com/developers/models/tripo3d/triposplat.md): `tripo3d/triposplat`. $0.05 / request. - Hunyuan3d V3 (Tencent), from $0.225: - [Hunyuan3d V3 · Image to 3D](https://doitong.com/developers/models/hunyuan3d-v3/image-to-3d.md): `hunyuan3d-v3/image-to-3d`. from $0.225 / run. - [Hunyuan3d V3 · Sketch to 3D](https://doitong.com/developers/models/hunyuan3d-v3/sketch-to-3d.md): `hunyuan3d-v3/sketch-to-3d`. $0.375 / run. - [Meshy 6 · Image to 3D](https://doitong.com/developers/models/meshy/v6/image-to-3d.md): `meshy/v6/image-to-3d`. Meshy 6 image-to-3D with remeshing, PBR maps, optional humanoid rigging and animation. from $0.80 / run. - [Meshy 6 Preview · Image to 3D](https://doitong.com/developers/models/meshy/v6-preview/image-to-3d.md): `meshy/v6-preview/image-to-3d`. Meshy 6 Preview image-to-3D with topology, polycount, PBR, rigging and animation options. from $0.80 / run. - Meshy 7.1 (Meshy), from $0.80: - [Meshy 7.1 Image to 3D](https://doitong.com/developers/models/meshy/v7.1/image-to-3d.md): `meshy/v7.1/image-to-3d`. from $0.80 / run. - [Meshy 7.1 Multi Image to 3D](https://doitong.com/developers/models/meshy/v7.1/multi-image-to-3d.md): `meshy/v7.1/multi-image-to-3d`. from $0.80 / run. - Tripo H3.1 (Tripo), from $0.20: - [Tripo H3.1 Image to 3D](https://doitong.com/developers/models/tripo3d/h3.1/image-to-3d.md): `tripo3d/h3.1/image-to-3d`. from $0.20 / run. - [Tripo H3.1 Multiview to 3D](https://doitong.com/developers/models/tripo3d/h3.1/multiview-to-3d.md): `tripo3d/h3.1/multiview-to-3d`. from $0.20 / run. - [Tripo P1 Image to 3D](https://doitong.com/developers/models/tripo3d/p1/image-to-3d.md): `tripo3d/p1/image-to-3d`. Single-image to 3D mesh with a low face budget and optional textures, the simpler P1 image variant. from $0.40 / request. - [Tripo P2 Image to 3D](https://doitong.com/developers/models/tripo3d/p2/image-to-3d.md): `tripo3d/p2/image-to-3d`. Image to 3D with PBR, quad topology, four texture quality levels and texture version selection. from $1.00 / run. - Hi3D (Hitem3D), from $0.50: - [Hi3D Image to 3D](https://doitong.com/developers/models/hitem3d/hi3d/image-to-3d.md): `hitem3d/hi3d/image-to-3d`. $0.50 / run (estimated per run). - [Hi3D Multiview to 3D · Multi View to 3D](https://doitong.com/developers/models/hitem3d/hi3d/multi-view-to-3d.md): `hitem3d/hi3d/multi-view-to-3d`. $0.50 / run (estimated per run). - Hunyuan 3D (Tencent), from $0.225: - [Hunyuan 3D Pro Image to 3D](https://doitong.com/developers/models/hunyuan-3d/v3.1/pro/image-to-3d.md): `hunyuan-3d/v3.1/pro/image-to-3d`. $0.375 / run. - [Hunyuan 3D Rapid Image to 3D](https://doitong.com/developers/models/hunyuan-3d/v3.1/rapid/image-to-3d.md): `hunyuan-3d/v3.1/rapid/image-to-3d`. from $0.225 / request. - Meshy v7 (Meshy), from $0.80: - [Meshy V7 Image to 3D](https://doitong.com/developers/models/meshy/v7/image-to-3d.md): `meshy/v7/image-to-3d`. from $0.80 / run. - [Meshy V7 Multi Image to 3D](https://doitong.com/developers/models/meshy/v7/multi-image-to-3d.md): `meshy/v7/multi-image-to-3d`. from $0.80 / run. ## Models: Text to 3D (14) - Hyper3D - Rodin V2.5 (Hyper3D), from $0.10: - [Hyper3D - Rodin V2.5 - Text to 3D](https://doitong.com/developers/models/hyper3d/rodin/v2.5/text-to-3d.md): `hyper3d/rodin/v2.5/text-to-3d`. from $0.40 / request. - [Hyper3D - Rodin V2.5 - Text to 3D - Fast](https://doitong.com/developers/models/hyper3d/rodin/v2.5/text-to-3d/fast.md): `hyper3d/rodin/v2.5/text-to-3d/fast`. $0.10 / request. - Hunyuan Motion (Tencent), from $0.06: - [Hunyuan Motion \[0.46B\]](https://doitong.com/developers/models/hunyuan-motion/fast.md): `hunyuan-motion/fast`. $0.06 / request. - [Hunyuan Motion \[1B\]](https://doitong.com/developers/models/hunyuan-motion.md): `hunyuan-motion`. $0.08 / request. - [Hunyuan3d V3 · Text to 3D](https://doitong.com/developers/models/hunyuan3d-v3/text-to-3d.md): `hunyuan3d-v3/text-to-3d`. Hunyuan3D V3 text-to-3D with Normal, LowPoly or Geometry output and PBR option. from $0.225 / run. - [Meshy 6 · Text to 3D](https://doitong.com/developers/models/meshy/v6/text-to-3d.md): `meshy/v6/text-to-3d`. Text-to-3D mesh generator with preview or textured modes, optional PBR, rigging and animation. $0.80 / request. - [Meshy 6 Preview · Text to 3D](https://doitong.com/developers/models/meshy/v6-preview/text-to-3d.md): `meshy/v6-preview/text-to-3d`. Meshy 6 Preview text-to-3D with preview or full textured mode and optional prompt expansion. $0.80 / request. - [Meshy 7.1 Text to 3D](https://doitong.com/developers/models/meshy/v7.1/text-to-3d.md): `meshy/v7.1/text-to-3d`. Meshy 7.1 text-to-3D with preview or full modes and geometry resolution up to 4k. from $0.80 / run. - [Tripo H3.1 Text to 3D](https://doitong.com/developers/models/tripo3d/h3.1/text-to-3d.md): `tripo3d/h3.1/text-to-3d`. Text-to-3D mesh generator with negative prompt, separate geometry and texture quality tiers, and a very high face cap. from $0.10 / run. - [Tripo P1 Text to 3D](https://doitong.com/developers/models/tripo3d/p1/text-to-3d.md): `tripo3d/p1/text-to-3d`. Text prompt to 3D mesh with a compact face range up to 20,000, the P1 text variant. $1.10 / run (estimated per run). - [Tripo P2 Text to 3D](https://doitong.com/developers/models/tripo3d/p2/text-to-3d.md): `tripo3d/p2/text-to-3d`. Text to 3D with PBR, quad meshes, selectable texture version and a negative prompt, the P2 text variant. from $1.00 / run. - Hunyuan 3D (Tencent), from $0.225: - [Hunyuan 3d](https://doitong.com/developers/models/hunyuan-3d/v3.1/rapid/text-to-3d.md): `hunyuan-3d/v3.1/rapid/text-to-3d`. from $0.225 / request. - [Hunyuan 3D Pro Text to 3D](https://doitong.com/developers/models/hunyuan-3d/v3.1/pro/text-to-3d.md): `hunyuan-3d/v3.1/pro/text-to-3d`. $0.375 / run. - [Meshy V7 Text to 3D](https://doitong.com/developers/models/meshy/v7/text-to-3d.md): `meshy/v7/text-to-3d`. Text-to-3D with Meshy 7: preview or full mode, 2k geometry, PBR, rigging and animation options. from $0.80 / run. ## Models: 3D (15) - [Sam 3 · 3D Align](https://doitong.com/developers/models/sam-3/3d-align.md): `sam-3/3d-align`. Aligns a SAM 3D body mesh to the scene of the source photo, optionally combining it with an object mesh. $0.02 / run (estimated per run). - Tripo3d (Tripo), from $0.40: - [Tripo3D Remesh](https://doitong.com/developers/models/tripo3d/tripo/remesh.md): `tripo3d/tripo/remesh`. $0.40 / run (estimated per run). - [Tripo3D Segment](https://doitong.com/developers/models/tripo3d/tripo/segment.md): `tripo3d/tripo/segment`. $0.40 / run (estimated per run). - [Abot World 0](https://doitong.com/developers/models/alibaba/abot-world-0.md): `alibaba/abot-world-0`. Interactive real-time explorable world session, set up via an SDP offer and ICE exchange. $0.001 / run (estimated per run). - Hi3D (Hitem3D), from $0.30: - [Hi3D 3D Part Splitter](https://doitong.com/developers/models/hitem3d/hi3d/split.md): `hitem3d/hi3d/split`. $0.40 / run (estimated per run). - [Hi3D 3D to Multicolor](https://doitong.com/developers/models/hitem3d/hi3d/multicolor.md): `hitem3d/hi3d/multicolor`. $0.40 / run (estimated per run). - [Hi3D Texture](https://doitong.com/developers/models/hitem3d/hi3d/texture.md): `hitem3d/hi3d/texture`. $0.30 / run (estimated per run). - Hunyuan 3D (Tencent), from $0.45: - [Hunyuan 3D Part Splitter](https://doitong.com/developers/models/hunyuan-3d/v3.1/part.md): `hunyuan-3d/v3.1/part`. $0.45 / run (estimated per run). - [Hunyuan 3D Smart Topology](https://doitong.com/developers/models/hunyuan-3d/v3.1/smart-topology.md): `hunyuan-3d/v3.1/smart-topology`. $0.75 / run (estimated per run). - [Lingbot World 2](https://doitong.com/developers/models/robbyant/lingbot-world-2.md): `robbyant/lingbot-world-2`. Real-time interactive world model session using a WebRTC-style offer and answer handshake. $0.001 / run (estimated per run). - [Meshy 6 Lite Retexture](https://doitong.com/developers/models/meshy/v6-lite/retexture.md): `meshy/v6-lite/retexture`. Lite tier of Meshy 6 retexturing: new textures for a 3D model from text or an image. $0.30 / request. - [Meshy 6 Retexture](https://doitong.com/developers/models/meshy/v6/retexture.md): `meshy/v6/retexture`. Re-textures an uploaded 3D model from a text prompt or style image, with optional PBR maps and up to 8k textures. from $0.30 / request. - Meshy Rigging (Meshy), from $0.20: - [Meshy Rigging](https://doitong.com/developers/models/meshy/rigging.md): `meshy/rigging`. from $0.20 / request. - [Meshy Rigging Multi Animation](https://doitong.com/developers/models/meshy/rigging/multi-animation.md): `meshy/rigging/multi-animation`. $0.20 / run. - [Meshy 7 Retexture](https://doitong.com/developers/models/meshy/v7/retexture.md): `meshy/v7/retexture`. Meshy 7 version of 3D retexturing: new look from a prompt or style image, with optional PBR output. from $0.30 / request. ## Models: Training (59) - [Ideogram V4.0q LoRA Trainer](https://doitong.com/developers/models/ideogram/v4/trainer.md): `ideogram/v4/trainer`. Trains a custom LoRA for Ideogram V4 from a zip of captioned images. $0.00675 / step. - [Krea 2 Trainer](https://doitong.com/developers/models/krea-2-trainer.md): `krea-2-trainer`. Trains a custom Krea 2 LoRA from a zip of images, with optional auto-captioning. from $0.30 / run. - [Phota Create Profile](https://doitong.com/developers/models/phota/create-profile.md): `phota/create-profile`. Creates a Phota identity profile from a zip of subject photos. $2.90 / request. - [Recraft V3 Create Style](https://doitong.com/developers/models/recraft/v3/create-style.md): `recraft/v3/create-style`. Creates a reusable Recraft V3 custom style from a zip of up to 5 PNG reference images. $0.04 / request. - [ERNIE-Image Trainer](https://doitong.com/developers/models/ernie-image-trainer.md): `ernie-image-trainer`. Trains a LoRA for Ernie Image from a zip of captioned images. $0.0012 / step. - Flux 2 Klein 9b Base Trainer (Black Forest Labs), from $4.30: - [FLUX 2 \[klein\] 9b Base Trainer](https://doitong.com/developers/models/flux-2-klein-9b-base-trainer.md): `flux-2-klein-9b-base-trainer`. $0.0043 / step. - [Flux 2 Klein 9B Base Trainer](https://doitong.com/developers/models/flux-2-klein-9b-base-trainer/edit.md): `flux-2-klein-9b-base-trainer/edit`. $0.0139 / step. - FLUX 2 Trainer (Black Forest Labs), from $6.40: - [FLUX 2 Trainer](https://doitong.com/developers/models/flux-2-trainer.md): `flux-2-trainer`. $0.0064 / step. - [FLUX 2 Trainer Edit](https://doitong.com/developers/models/flux-2-trainer/edit.md): `flux-2-trainer/edit`. $0.0389 / step. - FLUX 2 Trainer V2 (Black Forest Labs), from $6.40: - [FLUX 2 Trainer V2](https://doitong.com/developers/models/flux-2-trainer-v2.md): `flux-2-trainer-v2`. $0.0064 / step. - [FLUX 2 Trainer V2 Edit](https://doitong.com/developers/models/flux-2-trainer-v2/edit.md): `flux-2-trainer-v2/edit`. $0.0389 / step. - [Flux Kontext Trainer](https://doitong.com/developers/models/flux-kontext-trainer.md): `flux-kontext-trainer`. Trains a Kontext [dev] LoRA from a zip of paired start and end images. from $1.25 / run. - [Ideogram · Custom Models](https://doitong.com/developers/models/ideogram/custom-models.md): `ideogram/custom-models`. Trains a custom Ideogram model from a ZIP of 10-100 images. $40.00 / request. - LTX 2.3 Trainer (Lightricks), from $4.40: - [LTX 2.3 Trainer (V2) - Audio Inpainting](https://doitong.com/developers/models/ltx23-trainer-v2/audio-inpaint.md): `ltx23-trainer-v2/audio-inpaint`. $0.0023 / step. - [LTX 2.3 Trainer (V2) - Audio+Video Reference IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/av2av.md): `ltx23-trainer-v2/ic-lora/av2av`. $0.0068 / step. - [LTX 2.3 Trainer (V2) - Audio+Video Reference Transformation](https://doitong.com/developers/models/ltx23-trainer-v2/av2av.md): `ltx23-trainer-v2/av2av`. $0.0068 / step. - [LTX 2.3 Trainer (V2) - Audio-to-Audio](https://doitong.com/developers/models/ltx23-trainer-v2/a2a.md): `ltx23-trainer-v2/a2a`. $0.0023 / step. - [LTX 2.3 Trainer (V2) - Audio-to-Audio IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/a2a.md): `ltx23-trainer-v2/ic-lora/a2a`. $0.0023 / step. - [LTX 2.3 Trainer (V2) - Audio-to-Video](https://doitong.com/developers/models/ltx23-trainer-v2/a2v.md): `ltx23-trainer-v2/a2v`. $0.006 / step. - [LTX 2.3 Trainer (V2) - Backward Audio Extension](https://doitong.com/developers/models/ltx23-trainer-v2/audio-extend-suffix.md): `ltx23-trainer-v2/audio-extend-suffix`. $0.0023 / step. - [LTX 2.3 Trainer (V2) - Backward Video Extension](https://doitong.com/developers/models/ltx23-trainer-v2/extend-suffix.md): `ltx23-trainer-v2/extend-suffix`. $0.0061 / step. - [LTX 2.3 Trainer (V2) - Forward Audio Extension](https://doitong.com/developers/models/ltx23-trainer-v2/audio-extend-prefix.md): `ltx23-trainer-v2/audio-extend-prefix`. $0.0022 / step. - [LTX 2.3 Trainer (V2) - Forward Video Extension](https://doitong.com/developers/models/ltx23-trainer-v2/extend-prefix.md): `ltx23-trainer-v2/extend-prefix`. $0.0062 / step. - [LTX 2.3 Trainer (V2) - Image-to-Video](https://doitong.com/developers/models/ltx23-trainer-v2/i2v.md): `ltx23-trainer-v2/i2v`. $0.0024 / step. - [LTX 2.3 Trainer (V2) - Keyframe Interpolation](https://doitong.com/developers/models/ltx23-trainer-v2/interpolate.md): `ltx23-trainer-v2/interpolate`. $0.0024 / step. - [LTX 2.3 Trainer (V2) - Masked Audio+Video IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/av2av-masked.md): `ltx23-trainer-v2/ic-lora/av2av-masked`. $0.0068 / step. - [LTX 2.3 Trainer (V2) - Masked Audio+Video Transformation](https://doitong.com/developers/models/ltx23-trainer-v2/av2av-masked.md): `ltx23-trainer-v2/av2av-masked`. $0.0068 / step. - [LTX 2.3 Trainer (V2) - Masked Video-to-Video](https://doitong.com/developers/models/ltx23-trainer-v2/v2v-masked.md): `ltx23-trainer-v2/v2v-masked`. $0.0055 / step. - [LTX 2.3 Trainer (V2) - Masked Video-to-Video IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/v2v-masked.md): `ltx23-trainer-v2/ic-lora/v2v-masked`. $0.0055 / step. - [LTX 2.3 Trainer (V2) - Spatial Outpainting](https://doitong.com/developers/models/ltx23-trainer-v2/outpaint.md): `ltx23-trainer-v2/outpaint`. $0.006 / step. - [LTX 2.3 Trainer (V2) - Text-to-Audio](https://doitong.com/developers/models/ltx23-trainer-v2/t2a.md): `ltx23-trainer-v2/t2a`. $0.0022 / step. - [LTX 2.3 Trainer (V2) - Text-to-Video](https://doitong.com/developers/models/ltx23-trainer-v2/t2v.md): `ltx23-trainer-v2/t2v`. $0.006 / step. - [LTX 2.3 Trainer (V2) - Video Inpainting](https://doitong.com/developers/models/ltx23-trainer-v2/inpaint.md): `ltx23-trainer-v2/inpaint`. $0.0024 / step. - [LTX 2.3 Trainer (V2) - Video-to-Audio](https://doitong.com/developers/models/ltx23-trainer-v2/v2a.md): `ltx23-trainer-v2/v2a`. $0.0049 / step. - [LTX 2.3 Trainer (V2) - Video-to-Video](https://doitong.com/developers/models/ltx23-trainer-v2/v2v.md): `ltx23-trainer-v2/v2v`. $0.0059 / step. - [LTX 2.3 Trainer (V2) - Video-to-Video IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/v2v.md): `ltx23-trainer-v2/ic-lora/v2v`. $0.0059 / step. - [LTX-2.3 22B Video to Video Trainer](https://doitong.com/developers/models/ltx23-v2v-trainer.md): `ltx23-v2v-trainer`. Trains an LTX-2.3 22B LoRA for video transformation or video-conditioned generation from reference videos. $0.0135 / step. - [LTX-2.3 22B Video Trainer](https://doitong.com/developers/models/ltx23-video-trainer.md): `ltx23-video-trainer`. Trains an LTX-2.3 22B LoRA for custom video styles and effects, with optional audio. $0.0048 / step. - MiniMax H3 (MiniMax), from $10.00: - [MiniMax H3 First Last Frame LoRA Trainer](https://doitong.com/developers/models/minimax/h3/flf2v/trainer.md): `minimax/h3/flf2v/trainer`. $0.01 / step. - [MiniMax H3 Image to Video Audio LoRA Trainer](https://doitong.com/developers/models/minimax/h3/i2v/trainer.md): `minimax/h3/i2v/trainer`. $0.01 / step. - [MiniMax H3 Reference to Video LoRA Trainer](https://doitong.com/developers/models/minimax/h3/ref2va/trainer.md): `minimax/h3/ref2va/trainer`. $0.015 / step. - [MiniMax H3 Text to Video LoRA Trainer](https://doitong.com/developers/models/minimax/h3/t2v/trainer.md): `minimax/h3/t2v/trainer`. $0.005 / step. - [Qwen Image 2512 Trainer](https://doitong.com/developers/models/qwen-image-2512-trainer.md): `qwen-image-2512-trainer`. Trains a LoRA for Qwen Image 2512 from a zip of captioned images. from $0.75 / run. - [Qwen Image Edit 2509 Trainer](https://doitong.com/developers/models/qwen-image-edit-2509-trainer.md): `qwen-image-edit-2509-trainer`. Trains a custom LoRA for Qwen Image Edit 2509 from a zip of paired start and end images. from $0.40 / run. - Recraft V4 Styles (Recraft), from $0.005: - [Recraft V4 Styles Create Style](https://doitong.com/developers/models/recraft/v4/create-style.md): `recraft/v4/create-style`. $0.005 / request. - [Recraft V4 Styles Pro Create Style](https://doitong.com/developers/models/recraft/v4/pro/create-style.md): `recraft/v4/pro/create-style`. $0.005 / request. - [Stable Audio 3 Trainer](https://doitong.com/developers/models/stable-audio-3-trainer.md): `stable-audio-3-trainer`. Trains a LoRA on Stable Audio 3 from a zip of audio clips with matching text captions. from $0.003 / run. - [Train Flux LoRA](https://doitong.com/developers/models/flux-lora-fast-training.md): `flux-lora-fast-training`. Trains a Flux LoRA on a zip of your images to learn a person, subject or style. from $0.002 / run. - [Train Flux LoRAs For Portraits](https://doitong.com/developers/models/flux-lora-portrait-trainer.md): `flux-lora-portrait-trainer`. FLUX LoRA trainer tuned for portraits, with subject cropping and checkpoint resume. from $2.40 / run. - [TRELLIS.2 Trainer](https://doitong.com/developers/models/trellis-2-lora-trainer.md): `trellis-2-lora-trainer`. Trains LoRA adapters for Trellis 2 on a zip of 3D assets, for up to three denoisers. from $1.7508 / run. - [Turbo Flux Trainer](https://doitong.com/developers/models/turbo-flux-trainer.md): `turbo-flux-trainer`. Trains a FLUX dev LoRA on a zip of images, for either a subject or a style, with step and rate controls. $0.0024 / step. - [Wan 2.2 14B Image Trainer](https://doitong.com/developers/models/wan-22-image-trainer.md): `wan-22-image-trainer`. Trains a Wan 2.2 14B LoRA on your images for a subject or a style, returning low and high noise LoRA files. from $0.45 / run. - Wan-2.1 LoRA Trainer (Alibaba), from $2.00: - [Wan-2.1 LoRA Trainer · I2V 720p](https://doitong.com/developers/models/wan-trainer/i2v-720p.md): `wan-trainer/i2v-720p`. $0.005 / step. - [Wan-2.1 LoRA Trainer · T2V](https://doitong.com/developers/models/wan-trainer/t2v.md): `wan-trainer/t2v`. $0.005 / step. - [Wan-2.1 LoRA Trainer · T2V 14b](https://doitong.com/developers/models/wan-trainer/t2v-14b.md): `wan-trainer/t2v-14b`. $0.005 / step. - Wan-2.2 LoRA Trainer (Alibaba), from $1.60: - [Wan-2.2 LoRA Trainer · I2V A14b](https://doitong.com/developers/models/wan-22-trainer/i2v-a14b.md): `wan-22-trainer/i2v-a14b`. $0.005 / step. - [Wan-2.2 LoRA Trainer · T2V A14b](https://doitong.com/developers/models/wan-22-trainer/t2v-a14b.md): `wan-22-trainer/t2v-a14b`. $0.004 / step. - [Z Image Trainer](https://doitong.com/developers/models/z-image-trainer.md): `z-image-trainer`. Trains a LoRA for Z-Image Turbo from a zip of images, with content, style or balanced focus. $0.00226 / step. - [Z Image Turbo Trainer V2](https://doitong.com/developers/models/z-image-turbo-trainer-v2.md): `z-image-turbo-trainer-v2`. Trains a custom LoRA for Z Image Turbo from a zip of captioned images. from $0.425 / run. ## Models: LLM (14) - [Fibo · Structured Prompt](https://doitong.com/developers/models/bria/fibo/generate/structured_prompt.md): `bria/fibo/generate/structured_prompt`. Turns a prompt or reference image into Fibo's structured JSON description instead of rendering an image. $0.01 / request. - [Fibo Lite · Structured Prompt](https://doitong.com/developers/models/bria/fibo-lite/generate/structured_prompt.md): `bria/fibo-lite/generate/structured_prompt`. Converts text or an image into a Fibo Lite structured JSON prompt rather than producing a picture. $0.008 / request. - [Fibo Edit \[Structured Instruction\]](https://doitong.com/developers/models/bria/fibo-edit/edit/structured_instruction.md): `bria/fibo-edit/edit/structured_instruction`. Converts an edit request into a structured JSON description without producing an image. $0.01 / request. - [Mureka 9.5 Lyrics Generation](https://doitong.com/developers/models/mureka/api/generate/lyrics.md): `mureka/api/generate/lyrics`. Text-only model that writes song lyrics plus a title from a topic, theme or title idea. $0.0135 / request. - [Bytedance Seed V2 Mini](https://doitong.com/developers/models/bytedance/seed/v2/mini.md): `bytedance/seed/v2/mini`. Multimodal LLM that reads text, images and video, with switchable reasoning and multi-turn history. $0.0001 / 1000 tokens (charged by usage, up to $0.213 per run for the example input; the rest is refunded). - [Nemotron 3 Nano Omni](https://doitong.com/developers/models/nvidia/nemotron-3-nano-omni.md): `nvidia/nemotron-3-nano-omni`. Text-only chat LLM with switchable reasoning trace and up to 20,000 generated tokens. $0.01 / run (estimated per run). - [NVIDIA Nemotron 3.5 Super Text](https://doitong.com/developers/models/nvidia/nemotron-3-5-super/text.md): `nvidia/nemotron-3-5-super/text`. Text chat LLM with optional thinking mode that returns a separate reasoning trace, up to 32,000 tokens. $0.01 / run (estimated per run). - OpenRouter Router (OpenRouter), from $0.003: - [OpenRouter](https://doitong.com/developers/models/openrouter/router.md): `openrouter/router`. $0.01 / usage unit (charged by usage, up to $5.138 per run for the example input; the rest is refunded). - [OpenRouter \[Audio\]](https://doitong.com/developers/models/openrouter/router/audio.md): `openrouter/router/audio`. $0.01 / usage unit (charged by usage, up to $1.858 per run for the example input; the rest is refunded). - [OpenRouter \[Enterprise\]](https://doitong.com/developers/models/openrouter/router/enterprise.md): `openrouter/router/enterprise`. $0.01 / usage unit (charged by usage, up to $5.138 per run for the example input; the rest is refunded). - [OpenRouter \[Video\]](https://doitong.com/developers/models/openrouter/router/video.md): `openrouter/router/video`. $0.01 / usage unit (charged by usage, up to $1.858 per run for the example input; the rest is refunded). - [OpenRouter \[Video\]\[Enterprise\]](https://doitong.com/developers/models/openrouter/router/video/enterprise.md): `openrouter/router/video/enterprise`. $0.01 / usage unit (charged by usage, up to $1.858 per run for the example input; the rest is refunded). - [OpenRouter \[Vision\]](https://doitong.com/developers/models/openrouter/router/vision.md): `openrouter/router/vision`. $0.01 / usage unit (charged by usage, up to $14.34 per run for the example input; the rest is refunded). - [Video Prompt Generator](https://doitong.com/developers/models/video-prompt-generator.md): `video-prompt-generator`. Writes video-generation prompts from a concept, with camera, pacing and effects options. from $0.001 / request. ## Models: Vision (35) - [Bagel · Understand](https://doitong.com/developers/models/bagel/understand.md): `bagel/understand`. Answers a text question about an image, returning a written response. $0.05 / request. - [Bria Ad Delayer](https://doitong.com/developers/models/bria/ad-delayer.md): `bria/ad-delayer`. Splits a flat ad image into editable layers and returns a structured JSON description. $0.30 / request. - [Sam 3 · Image · Embed](https://doitong.com/developers/models/sam-3/image/embed.md): `sam-3/image/embed`. Computes a SAM 3 embedding for an image and returns it as a base64 string. $0.005 / run (estimated per run). - Nemotron 3 Nano Omni (NVIDIA), from $0.012: - [Nemotron 3 Nano Omni · Video](https://doitong.com/developers/models/nvidia/nemotron-3-nano-omni/video.md): `nvidia/nemotron-3-nano-omni/video`. $0.006 / 1000 tokens (charged by usage, up to $0.193 per run for the example input; the rest is refunded). - [Nemotron 3 Nano Omni · Vision](https://doitong.com/developers/models/nvidia/nemotron-3-nano-omni/vision.md): `nvidia/nemotron-3-nano-omni/vision`. $0.018 / run (estimated per run). - NVIDIA Nemotron 3.5 Super (NVIDIA), from $0.01: - [NVIDIA Nemotron 3.5 Super Video](https://doitong.com/developers/models/nvidia/nemotron-3-5-super/video.md): `nvidia/nemotron-3-5-super/video`. $0.01 / 1000 tokens (charged by usage, up to $0.322 per run for the example input; the rest is refunded). - [NVIDIA Nemotron 3.5 Super Vision](https://doitong.com/developers/models/nvidia/nemotron-3-5-super/vision.md): `nvidia/nemotron-3-5-super/vision`. $0.01 / run (estimated per run). - Florence 2 Large (Microsoft), from $0.003: - [Florence 2 Large Caption](https://doitong.com/developers/models/florence-2-large/caption.md): `florence-2-large/caption`. $0.003 / run (estimated per run). - [Florence 2 Large Detailed Caption](https://doitong.com/developers/models/florence-2-large/detailed-caption.md): `florence-2-large/detailed-caption`. $0.004 / run (estimated per run). - [Florence 2 Large OCR](https://doitong.com/developers/models/florence-2-large/ocr.md): `florence-2-large/ocr`. $0.003 / run (estimated per run). - [Florence 2 Large Region To Category](https://doitong.com/developers/models/florence-2-large/region-to-category.md): `florence-2-large/region-to-category`. $0.003 / run (estimated per run). - [Florence-2 Large · More Detailed Caption](https://doitong.com/developers/models/florence-2-large/more-detailed-caption.md): `florence-2-large/more-detailed-caption`. $0.004 / run (estimated per run). - [Florence-2 Large · Region to Description](https://doitong.com/developers/models/florence-2-large/region-to-description.md): `florence-2-large/region-to-description`. $0.003 / run (estimated per run). - [GOT OCR 2.0](https://doitong.com/developers/models/got-ocr/v2.md): `got-ocr/v2`. OCR model that reads text from one or more image URLs, with optional formatted output and multi-page merging. $0.05 / run (estimated per run). - [NSFW Filter](https://doitong.com/developers/models/imageutils/nsfw.md): `imageutils/nsfw`. Scores an image with the probability that it is NSFW, returned as a number rather than an image. $0.001 / image. - [Isaac 0.1](https://doitong.com/developers/models/perceptron/isaac-01.md): `perceptron/isaac-01`. Vision-language model that answers about an image as text, boxes, points or polygons. $0.001 / run (estimated per run). - [LLaVA v1.6 34B](https://doitong.com/developers/models/llava-next.md): `llava-next`. Multimodal vision-language model that answers a text prompt about a single image. $0.009 / run (estimated per run). - [Moondream](https://doitong.com/developers/models/moondream/batched.md): `moondream/batched`. Answers questions about many images in one call by taking a list of prompt and image URL pairs. $0.004 / run (estimated per run). - Moondream2 (Moondream), from $0.01: - [Moondream2](https://doitong.com/developers/models/moondream2.md): `moondream2`. $0.01 / run (estimated per run). - [Moondream2 · Object Detection](https://doitong.com/developers/models/moondream2/object-detection.md): `moondream2/object-detection`. $0.02 / image. - [Moondream2 · Point Object Detection](https://doitong.com/developers/models/moondream2/point-object-detection.md): `moondream2/point-object-detection`. $0.02 / image. - [Moondream2 · Visual Query](https://doitong.com/developers/models/moondream2/visual-query.md): `moondream2/visual-query`. $0.01 / 1000 characters. - Moondream3 Preview (Moondream), from $0.001: - [Moondream 3 Preview \[Query\]](https://doitong.com/developers/models/moondream3-preview/query.md): `moondream3-preview/query`. $0.001 / run (estimated per run). - [Moondream3 Preview \[Caption\]](https://doitong.com/developers/models/moondream3-preview/caption.md): `moondream3-preview/caption`. $0.002 / run (estimated per run). - [Moondream3 Preview \[Detect\]](https://doitong.com/developers/models/moondream3-preview/detect.md): `moondream3-preview/detect`. $0.001 / run (estimated per run). - [Moondream3 Preview \[Point\]](https://doitong.com/developers/models/moondream3-preview/point.md): `moondream3-preview/point`. $0.001 / run (estimated per run). - Moondreamnext (Moondream), from $0.002: - [MoonDreamNext](https://doitong.com/developers/models/moondream-next.md): `moondream-next`. $0.002 / run (estimated per run). - [MoonDreamNext Batch](https://doitong.com/developers/models/moondream-next/batch.md): `moondream-next/batch`. $0.002 / run (estimated per run). - [Nemotron Diffusion Vlm](https://doitong.com/developers/models/nemotron-diffusion-vlm.md): `nemotron-diffusion-vlm`. Vision-language model that answers prompts about an image using diffusion-based text decoding. $0.005 / run (estimated per run). - [NSFW Checker](https://doitong.com/developers/models/x-ailab/nsfw.md): `x-ailab/nsfw`. Classifies images as NSFW or safe, returning a boolean per image. $0.001 / run of input image. - Sa2VA (ByteDance), from $0.02: - [Sa2VA 4B Image](https://doitong.com/developers/models/sa2va/4b/image.md): `sa2va/4b/image`. $0.02 / image. - [Sa2VA 4B Video](https://doitong.com/developers/models/sa2va/4b/video.md): `sa2va/4b/video`. $0.04 / second of input video. - [Sa2VA 8B Image](https://doitong.com/developers/models/sa2va/8b/image.md): `sa2va/8b/image`. $0.04 / image. - [Sa2VA 8B Video](https://doitong.com/developers/models/sa2va/8b/video.md): `sa2va/8b/video`. $0.08 / second of input video. - [VGGT-1B](https://doitong.com/developers/models/vggt-1b.md): `vggt-1b`. Reconstructs a 3D scene from up to 48 images or a video, returning depth maps, camera poses and a point cloud. $0.000975 / second of processing time (charged by usage, up to $1.755 per run for the example input; the rest is refunded). ## Models: Other (5) - FFmpeg API (Utility), from $0.001: - [FFmpeg API Metadata](https://doitong.com/developers/models/ffmpeg-api/metadata.md): `ffmpeg-api/metadata`. $0.001 / run (estimated per run). - [FFmpeg API Waveform](https://doitong.com/developers/models/ffmpeg-api/waveform.md): `ffmpeg-api/waveform`. $0.001 / run (estimated per run). - Omnilottie (Open model), from $0.05: - [Omnilottie](https://doitong.com/developers/models/omnilottie.md): `omnilottie`. $0.05 / image. - [Omnilottie · Image to Lottie](https://doitong.com/developers/models/omnilottie/image-to-lottie.md): `omnilottie/image-to-lottie`. $0.10 / image. - [Omnilottie · Video to Lottie](https://doitong.com/developers/models/omnilottie/video-to-lottie.md): `omnilottie/video-to-lottie`. $0.05 / video. ## Machine-readable - [OpenAPI 3.1 document](https://doitong.com/developers/openapi.json): every endpoint, typed request bodies of the featured models; add ?model=, ?category= or ?models=all - [Model catalog as JSON](https://api.doitong.ru/v1/models): `GET`, no key needed ## Optional - [Everything in one file](https://doitong.com/developers/llms-full.txt): all guides, featured models in full, essentials of every other model