# OpenRouter [Vision] API

> Menghalakan prompt dengan imej atau PDF kepada LLM multimodal terpilih untuk kapsyen, OCR atau soal jawab visual

Menerima `prompt` dan nama model bahasa berkeupayaan visi dalam `model`, kemudian mengembalikan jawapan teks. Lampirkan gambar melalui `image_urls` dan dokumen melalui `pdf_urls`, yang hanya menerima fail PDF. Turut menyokong `system_prompt`, `temperature` daripada 0 hingga 2, `max_tokens`, output penaakulan pilihan dan carian web.

- Model id: `openrouter/router/vision`
- Made by: OpenRouter
- Category: LLM
- Output: text
- Charged by usage (up to $14.34 per run, typical $0.026; the rest of the hold is refunded): $0.01 / usage unit (cheapest run $0.026 (26 API credits))
- Run: `POST https://api.doitong.com/v1/run/openrouter/router/vision`
- Quote: `POST https://api.doitong.com/v1/quote/openrouter/router/vision`
- Docs page: https://doitong.com/ms/developers/models/openrouter/router/vision

## Pricing

Price: **$0.01 / usage unit**. Charged by actual usage at $0.01 / usage unit: up to $14.34 per run (the quote gives the maximum for your input), the rest is refunded automatically after the run. A typical run costs $0.026.

The full example input below holds up to $14.34 = 14340 API credits (up to 1434 units × $0.01) when it starts; a typical run costs $0.026 (26 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). This model is charged by usage: `POST https://api.doitong.com/v1/quote/openrouter/router/vision` with the same JSON body returns the most the run can cost for that input (`credits`, debited when the run starts); after the run you pay the usage the model reports and the rest is refunded automatically. An input whose maximum would exceed the per-run limit is refused with 422. 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 |
|---|---|---|---|---|---|---|
| `image_urls` | `images` | array of image URL \| null | no |  |  | URL yang mengenal pasti imej untuk diproses. |
| `pdf_urls` |  | array of string \| null | no |  |  | Berikan lokasi dokumen sebagai senarai yang hanya mengandungi PDF: URL http(s) yang menunjuk ke fail .pdf atau URI data dalam bentuk data:application/pdf;base64,... . Penghurai dokumen OpenRouter mengendalikannya apabila model tidak dapat memproses PDF secara natif. |
| `prompt` |  | string | yes |  |  | Prompt yang digunakan pada imej. |
| `system_prompt` |  | string \| null | no |  |  | Prompt sistem yang membekalkan arahan atau konteks kepada model. |
| `model` |  | string | yes |  |  | Nama yang mengenal pasti model untuk dijalankan. |
| `reasoning` |  | boolean | no | `false` |  | Sama ada untuk menyertakan penaakulan dalam respons akhir. |
| `temperature` |  | number | no | `1` | 0 – 2 | Kawalan kepelbagaian respons, dengan 0 menjamin jawapan yang sama apabila input tidak berubah. Meningkatkan nilai mengalihkan respons daripada jawapan yang boleh dijangka dan lazim kepada jawapan yang lebih pelbagai dan kurang biasa. |
| `max_tokens` |  | integer \| null | no |  | ≥ 1 | Hadkan bilangan token yang dijana dalam respons kepada nilai yang tidak melebihi panjang konteks ditolak panjang prompt. Penjanaan tidak boleh melebihi had yang ditentukan. |
| `enable_web_search` |  | boolean | no | `false` |  | Suis akses web yang membolehkan model memilih sama ada dan bila hendak mencari, termasuk berbilang carian dalam satu permintaan. Carian menggunakan alat carian web sisi pelayan OpenRouter untuk mendapatkan maklumat masa nyata. |
| `web_search_options` |  | object {engine, max_results, max_uses, max_total_results, search_context_size, max_characters, allowed_domains, excluded_domains, user_location} \| null | no |  |  | Konfigurasi carian web, termasuk pemilihan enjin, had hasil dan penapisan domain. Hanya digunakan apabila enable_web_search ialah true. |
| `web_search_options.engine` |  | enum (string) | no | `auto` | `auto`, `native`, `exa` | Pemilihan enjin carian: 'auto' dan 'native' kedua-duanya beralih kepada Exa apabila carian asli tidak tersedia. 'auto' menggunakan carian asli penyedia yang tersedia; 'native' mengutamakan carian terbina dalam OpenAI, Anthropic, Google, xAI atau Perplexity. Untuk menggunakan API carian Exa sahaja, pilih 'exa'. |
| `web_search_options.max_results` |  | integer \| null | no |  | 1 – 25 | Had hasil bagi setiap panggilan carian Exa, dari 1 hingga 25, dengan lalai 5. Carian penyedia asli mengabaikan tetapan ini. |
| `web_search_options.max_uses` |  | integer \| null | no |  | ≥ 1 | Had carian setiap permintaan, dihantar kepada Anthropic untuk carian asli tetapi diabaikan oleh penyedia asli lain. Panggilan yang melebihi had menerima hasil ralat dan tidak dijalankan. |
| `web_search_options.max_total_results` |  | integer \| null | no |  | ≥ 1 | Had hasil gabungan untuk semua carian dalam satu permintaan. |
| `web_search_options.search_context_size` |  | enum (string) \| null | no |  | `low`, `medium`, `high` | Jumlah pengambilan setiap hasil untuk Exa, digantikan oleh max_characters jika kedua-duanya dibekalkan dan diabaikan untuk carian penyedia asli. Pilih low untuk 5K aksara, medium untuk 15K atau high untuk 30K; jika tidak dinyatakan, Exa menyesuaikan jumlah kepada kira-kira 2–4K setiap hasil. |
| `web_search_options.max_characters` |  | integer \| null | no |  | 1 – 100,000 | Had aksara kandungan setiap hasil untuk Exa, mengatasi search_context_size jika kedua-dua tetapan dibekalkan. Tetapkan maksimum tepat dari 1 hingga 100,000 aksara; carian penyedia asli mengabaikan tetapan ini. |
| `web_search_options.allowed_domains` |  | array of string \| null | no |  |  | Senarai benarkan domain untuk Exa dan kebanyakan penyedia carian asli, mengehadkan hasil kepada domain yang disenaraikan. Carian asli Google tidak menyokongnya. |
| `web_search_options.excluded_domains` |  | array of string \| null | no |  |  | Senarai pengecualian domain untuk carian Exa dan penyedia asli yang serasi; carian asli Google dan OpenAI tidak boleh menggunakan senarai ini. Hasil daripada domain yang disenaraikan dikecualikan. |
| `web_search_options.user_location` |  | object {type, city, region, country, timezone} \| null | no |  |  | Lokasi pengguna anggaran yang mempengaruhi hasil carian asli secara geografi; Exa tidak menggunakan maklumat ini. |
| `web_search_options.user_location.type` |  | string | no | `approximate` |  | Klasifikasi lokasi; satu-satunya nilai yang disokong ialah 'approximate'. |
| `web_search_options.user_location.city` |  | string \| null | no |  |  | Nama bandar, seperti 'San Francisco'. |
| `web_search_options.user_location.region` |  | string \| null | no |  |  | Nama negeri atau wilayah, seperti 'California'. |
| `web_search_options.user_location.country` |  | string \| null | no |  |  | Pengecam negara yang dinyatakan sebagai dua huruf, seperti 'US'. |
| `web_search_options.user_location.timezone` |  | string \| null | no |  |  | Pengecam zon waktu dalam tatatanda IANA, seperti 'America/Los_Angeles'. |

File parameters (`images`) 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",
  "model": "openai/gpt-6-sol"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "model": "openai/gpt-6-sol"
}
```

## 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.com/v1/run/openrouter/router/vision?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",
    "model": "openai/gpt-6-sol"
  }'

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

### JavaScript

```javascript
const API = "https://api.doitong.com/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/openrouter/router/vision?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",
    "model": "openai/gpt-6-sol"
  }),
});
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.com/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",
    "model": "openai/gpt-6-sol",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/openrouter/router/vision", 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.com/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": "openrouter/router/vision",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "model": "openai/gpt-6-sol"
      },
      "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": "openrouter/router/vision",
  "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": 14340,
    "usd": "14.34",
    "charged": 14340,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "model": "openai/gpt-6-sol"
  },
  "output": {
    "output": "A close-up of a tiger's face focusing on its bright orange iris and the area around its eye, with white fur eyebrows and a contrasting black and rich orange striped fur pattern. The word \"FLUX\" is overlaid in bold, white, brush-stroke styled text across the tiger's face.",
    "usage": {
      "prompt_tokens": 1,
      "completion_tokens": 1,
      "total_tokens": 0,
      "cost": 1.0,
      "prompt_tokens_details": {
        "cached_tokens": 0,
        "cache_write_tokens": 0
      }
    }
  },
  "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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `output` | string | Hasil yang dihasilkan oleh model. |
| `usage` | object {prompt_tokens, completion_tokens, total_tokens, cost, prompt_tokens_details} \| null | Butiran penggunaan token. |

## Related models

- [OpenRouter](https://doitong.com/developers/models/openrouter/router.md) (`openrouter/router`): $0.01 / usage unit
- [OpenRouter \[Audio\]](https://doitong.com/developers/models/openrouter/router/audio.md) (`openrouter/router/audio`): $0.01 / usage unit
- [OpenRouter \[Enterprise\]](https://doitong.com/developers/models/openrouter/router/enterprise.md) (`openrouter/router/enterprise`): $0.01 / usage unit
- [OpenRouter \[Video\]](https://doitong.com/developers/models/openrouter/router/video.md) (`openrouter/router/video`): $0.01 / usage unit
- [OpenRouter \[Video\]\[Enterprise\]](https://doitong.com/developers/models/openrouter/router/video/enterprise.md) (`openrouter/router/video/enterprise`): $0.01 / usage unit
- [Bytedance Seed V2 Mini](https://doitong.com/developers/models/bytedance/seed/v2/mini.md) (`bytedance/seed/v2/mini`): $0.0001 / 1000 tokens
- [Fibo Edit \[Structured Instruction\]](https://doitong.com/developers/models/bria/fibo-edit/edit/structured_instruction.md) (`bria/fibo-edit/edit/structured_instruction`): $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`): $0.008 / request

## Links

- HTML page: https://doitong.com/developers/models/openrouter/router/vision
- 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=openrouter/router/vision
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/openrouter/router/vision