# Sa2VA 8B Video API

> 프레임 전반의 비디오 질의응답과 객체 마스크를 지원하는 대형 8B Sa2VA 모델

`video_url`과 텍스트 `prompt`를 받아 텍스트 답변과 레이블이 지정된 마스크 비디오를 반환합니다. `num_frames_to_sample`은 샘플링할 프레임 수를 5 to 100으로 제어하며, 생략하면 32가 사용됩니다. 비디오 입력용 8B 크기 모델입니다.

- Model id: `sa2va/8b/video`
- Made by: ByteDance
- Category: Vision
- Output: text
- Price per second of your input video: $0.08 / second of input video (cheapest run $0.08 (80 API credits))
- Run: `POST https://api.doitong.ru/v1/run/sa2va/8b/video`
- Quote: `POST https://api.doitong.ru/v1/quote/sa2va/8b/video`
- Docs page: https://doitong.com/ko/developers/models/sa2va/8b/video

## Pricing

Price: **$0.08 / second of input video**. Price per second of your input video: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $0.80 = 800 API credits (10 s input video × $0.08).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.ru/v1/quote/sa2va/8b/video` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | 채팅 완료에 제공하는 프롬프트입니다. |
| `video_url` | `video` | string (video URL) | yes |  |  | 입력 동영상을 가리키는 URL입니다. |
| `num_frames_to_sample` |  | integer \| null | no |  | 5 – 100 | 샘플링할 동영상 프레임 수로, 5에서 100 사이입니다. 생략하면 32를 사용합니다. |

File parameters (`video`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/sa2va/8b/video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/sa2va/8b/video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/sa2va/8b/video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.ru/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "sa2va/8b/video",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "sa2va/8b/video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 800,
    "usd": "0.80",
    "charged": 800,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "output": {
    "output": "<p>  Two children  </p>   [SEG]  are jumping on  <p>  a bed  </p>   [SEG]  .<|im_end|>",
    "masks": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      }
    ]
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `output` | string | 모델이 생성한 결과입니다. |
| `masks` | array of object {url, content_type, file_name, file_size} | 레이블을 마스크 동영상에 매핑하는 사전입니다. |

## Related models

- [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
- [Bagel · Understand](https://doitong.com/developers/models/bagel/understand.md) (`bagel/understand`): $0.05 / request
- [Bria Ad Delayer](https://doitong.com/developers/models/bria/ad-delayer.md) (`bria/ad-delayer`): $0.30 / request
- [Florence 2 Large Caption](https://doitong.com/developers/models/florence-2-large/caption.md) (`florence-2-large/caption`): $0.003 / 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
- [Florence 2 Large OCR](https://doitong.com/developers/models/florence-2-large/ocr.md) (`florence-2-large/ocr`): $0.003 / run

## Links

- HTML page: https://doitong.com/developers/models/sa2va/8b/video
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=sa2va/8b/video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/sa2va/8b/video