# Moondream API

> Trả lời câu hỏi về nhiều hình ảnh trong một lần gọi bằng cách nhận danh sách các cặp lời nhắc và URL hình ảnh

Phiên bản hàng loạt của mô hình ngôn ngữ-hình ảnh Moondream. Truyền danh sách đối tượng trong `inputs`, mỗi đối tượng chứa một lời nhắc và URL hình ảnh, rồi nhận danh sách đầu ra được tạo cùng tên tệp và thời gian xử lý. Việc tạo sinh được điều chỉnh bằng `max_tokens` (32 đến 1024, mặc định 64), `temperature` (0 đến 1), `top_p` và `repetition_penalty` (1 đến 2). Phản hồi cũng có cờ cho biết kết quả có phải là một phần hay không.

- Model id: `moondream/batched`
- Made by: Moondream
- Category: Vision
- Output: json
- Estimated price per run: $0.004 / run (cheapest run $0.004 (4 API credits))
- Run: `POST https://api.doitong.ru/v1/run/moondream/batched`
- Quote: `POST https://api.doitong.ru/v1/quote/moondream/batched`
- Docs page: https://doitong.com/vi/developers/models/moondream/batched

## Pricing

Price: **$0.004 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $0.004 = 4 API credits (1 request × 4 API credits).

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/moondream/batched` 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

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `inputs` |  | array of object {image_url, prompt} | yes |  |  | Danh sách chứa các lời nhắc đầu vào và URL hình ảnh. |
| `inputs[].image_url` |  | string (image URL) | yes |  |  | URL trỏ đến hình ảnh cần xử lý. |
| `inputs[].prompt` |  | string | no | `Describe this image.` |  | Lời nhắc áp dụng cho hình ảnh. |
| `max_tokens` |  | integer | no | `64` | 32 – 1,024 | Giới hạn trên của số token mới được tạo. |
| `temperature` |  | number | no | `0.2` | ≤ 1, > 0 | Cài đặt nhiệt độ lấy mẫu. |
| `top_p` |  | number | no | `1` | 0 – 1 | Cài đặt top-P lấy mẫu. |
| `repetition_penalty` |  | number | no | `1` | 1 – 2 | Mức phạt áp dụng cho việc lặp lại khi lấy mẫu. |

## Example input

Required parameters only:

```json
{
  "inputs": [
    {
      "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    }
  ]
}
```

A fuller example:

```json
{
  "inputs": [
    {
      "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    }
  ]
}
```

## 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/moondream/batched?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "inputs": [
      {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
      }
    ]
  }'

# 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/moondream/batched?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "inputs": [
      {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
      }
    ]
  }),
});
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 = {
    "inputs": [
        {
            "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
        },
    ],
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/moondream/batched", 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": "moondream/batched",
      "input": {
        "inputs": [
          {
            "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
          }
        ]
      },
      "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": "moondream/batched",
  "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": 4,
    "usd": "0.004",
    "charged": 4,
    "refunded": 0
  },
  "input": {
    "inputs": [
      {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
      }
    ]
  },
  "output": {
    "outputs": [
      "string"
    ],
    "partial": false,
    "timings": {},
    "filenames": [
      "string"
    ]
  },
  "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 |
|---|---|---|
| `outputs` | array of string | Danh sách chứa các kết quả được tạo. |
| `partial` | boolean | Cho biết đầu ra có chưa hoàn tất hay không. |
| `timings` | object | Các phép đo thời gian cho từng giai đoạn xử lý. |
| `filenames` | array of string \| null | Tên các tệp hình ảnh đã xử lý. |

## Related models

- [Moondream 3 Preview \[Query\]](https://doitong.com/developers/models/moondream3-preview/query.md) (`moondream3-preview/query`): $0.001 / run
- [Moondream2](https://doitong.com/developers/models/moondream2.md) (`moondream2`): $0.01 / 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 \[Caption\]](https://doitong.com/developers/models/moondream3-preview/caption.md) (`moondream3-preview/caption`): $0.002 / run
- [Moondream3 Preview \[Detect\]](https://doitong.com/developers/models/moondream3-preview/detect.md) (`moondream3-preview/detect`): $0.001 / run
- [Moondream3 Preview \[Point\]](https://doitong.com/developers/models/moondream3-preview/point.md) (`moondream3-preview/point`): $0.001 / run

## Links

- HTML page: https://doitong.com/developers/models/moondream/batched
- 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=moondream/batched
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/moondream/batched