# OpenRouter [Video] API

> Varianta da gateway LLM per analisar u resumir videos furnids sco URLs, cun in prompt da text

Elavura in u plirs videos inditgads en `video_urls` ensemen cun in `prompt` ed in `model` obligatoric. Ils formats enumerads èn mp4, mpeg, mov e webm, e links YouTube funcziunan en tscherts cas. Porscha er `system_prompt`, `temperature`, `max_tokens`, `reasoning` e tschertga web. Retorna text e l’utilisaziun da tokens.

- Model id: `openrouter/router/video`
- Made by: OpenRouter
- Category: LLM
- Output: text
- Charged by usage (up to $1.858 per run, typical $0.008; the rest of the hold is refunded): $0.01 / usage unit (cheapest run $0.008 (8 API credits))
- Run: `POST https://api.doitong.com/v1/run/openrouter/router/video`
- Quote: `POST https://api.doitong.com/v1/quote/openrouter/router/video`
- Docs page: https://doitong.com/rm/developers/models/openrouter/router/video

## Pricing

Price: **$0.01 / usage unit**. Charged by actual usage at $0.01 / usage unit: up to $1.858 per run (the quote gives the maximum for your input), the rest is refunded automatically after the run. A typical run costs $0.008.

The full example input below holds up to $1.858 = 1858 API credits (up to 185.7946 units × $0.01) when it starts; a typical run costs $0.008 (8 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/video` 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 |
|---|---|---|---|---|---|---|
| `video_urls` | `videos` | array of video URL \| null | no |  |  | Inputs video furnids sco array empè da `video_url`; ils dus na pon betg vegnir utilisads ensemen. URLs da YouTube èn acceptadas cun Google Gemini via AI Studio; autramain furnescha URLs da datotecas u URIs da datas per videos mp4, mpeg, mov u webm. |
| `prompt` |  | string | yes |  |  | Prompt che dirigia il processament da video. |
| `system_prompt` |  | string \| null | no |  |  | Prompt dal sistem che furnescha al model instrucziuns u context. |
| `model` |  | string | yes |  |  | Num che identifitgescha il model da exequir. |
| `reasoning` |  | boolean | no | `false` |  | Inditgescha sch’il raschunament duai vegnir inclus en la resposta finala. |
| `temperature` |  | number | no | `1` | 0 – 2 | Controlla da la variabladad da la resposta, cun 0 che garantescha la medema resposta sch’il input resta invarià. Augmentar la valur allontanescha las respostas da respostas prevediblas e tipicas vers dapli diversitad e respostas pli raras. |
| `max_tokens` |  | integer \| null | no |  | ≥ 1 | Limita il dumber da tokens generads da la resposta ad ina valur betg pli gronda che la lunghezza dal context minus la lunghezza dal prompt. La generaziun na po betg surpassar questa limita. |
| `enable_web_search` |  | boolean | no | `false` |  | Interrupziun per l’access web che permetta al model da tscherner sch’ed cura tschertgar, inclus pliras tschertgas en ina dumonda. Las tschertgas utiliseschan l’utensil da tschertga web dal server OpenRouter per infurmaziuns actualas. |
| `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 |  |  | Configuraziun da la tschertga web, inclus selecziun dal motor, limits da resultats e filtraziun da domens. Utilisada mo sche enable_web_search è true. |
| `web_search_options.engine` |  | enum (string) | no | `auto` | `auto`, `native`, `exa` | Selecziun dal motor da tschertga: 'auto' e 'native' recurran omadus a Exa sch’ina tschertga nativa na vegn betg sustegnida. 'auto' utilisescha la tschertga nativa disponibla dal provider; 'native' preferescha la tschertga integrada da OpenAI, Anthropic, Google, xAI u Perplexity. Per utilisar exclusivamain l’API da tschertga da Exa, tscherna 'exa'. |
| `web_search_options.max_results` |  | integer \| null | no |  | 1 – 25 | Limita dals resultats per mintga clom da tschertga Exa, da 1 fin 25, cun in standard da 5. La tschertga nativa dal provider ignora questa configuraziun. |
| `web_search_options.max_uses` |  | integer \| null | no |  | ≥ 1 | Limita da tschertgas per dumonda, transmesa ad Anthropic per la tschertga nativa ma ignorada dals auters providers nativs. Cloms sur la limita survegnan in resultat d’error e na vegnan betg exequids. |
| `web_search_options.max_total_results` |  | integer \| null | no |  | ≥ 1 | Limita cumina da resultats per tut las tschertgas entaifer ina dumonda. |
| `web_search_options.search_context_size` |  | enum (string) \| null | no |  | `low`, `medium`, `high` | Quantitad da recuperaziun per resultat tar Exa, remplazzada da max_characters sch’omisduas vegnan furnidas e ignorada per la tschertga nativa. Tscherna low per 5K caracters, medium per 15K u high per 30K; senza indicaziun adatta Exa la quantitad a circa 2–4K per resultat. |
| `web_search_options.max_characters` |  | integer \| null | no |  | 1 – 100,000 | Limita da caracters dal cuntegn per resultat tar Exa, che surpiglia search_context_size sch’omisduas configuraziuns vegnan furnidas. Definescha ina maxima exacta da 1 fin 100,000 caracters; la tschertga nativa ignora questa configuraziun. |
| `web_search_options.allowed_domains` |  | array of string \| null | no |  |  | Allowlist da domens per Exa e la gronda part dals providers nativs, che restrenscha ils resultats als domens inditgads. La tschertga nativa da Google na la sustegna betg. |
| `web_search_options.excluded_domains` |  | array of string \| null | no |  |  | Glista d’exclusiun da domens per tschertgas Exa e providers nativs cumpatibels; las tschertgas nativas da Google e OpenAI na pon betg applicar questa glista. Resultats da domens inditgads vegnan exclus. |
| `web_search_options.user_location` |  | object {type, city, region, country, timezone} \| null | no |  |  | Lieu approximativ da l’utilisader che influenzescha geograficamain ils resultats da la tschertga nativa; Exa na utilisescha betg quest’infurmaziun. |
| `web_search_options.user_location.type` |  | string | no | `approximate` |  | Classificaziun dal lieu; l’unica valur sustegnida è 'approximate'. |
| `web_search_options.user_location.city` |  | string \| null | no |  |  | Num da la citad, sco 'San Francisco'. |
| `web_search_options.user_location.region` |  | string \| null | no |  |  | Num dal stadi u da la regiun, sco 'California'. |
| `web_search_options.user_location.country` |  | string \| null | no |  |  | Identificatì dal pajais exprimì cun duas letras, sco 'US'. |
| `web_search_options.user_location.timezone` |  | string \| null | no |  |  | Identificatì dal fusi temporal en notaziun IANA, sco 'America/Los_Angeles'. |

File parameters (`videos`) 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": "google/gemini-3.8-flash"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "model": "google/gemini-3.8-flash"
}
```

## 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/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",
    "model": "google/gemini-3.8-flash"
  }'

# 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/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",
    "model": "google/gemini-3.8-flash"
  }),
});
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": "google/gemini-3.8-flash",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/openrouter/router/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.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/video",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "model": "google/gemini-3.8-flash"
      },
      "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/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": 1858,
    "usd": "1.858",
    "charged": 1858,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "model": "google/gemini-3.8-flash"
  },
  "output": {
    "output": "that's the way I look at it and I don't know what you would say. Sooner or later the child gets run over.\nThey seem to be too local, too provincial.",
    "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 | Resultat producì dal processament dal video. |
| `usage` | object {prompt_tokens, completion_tokens, total_tokens, cost, prompt_tokens_details} \| null | Detagls dal consum da tokens. |

## 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 \[Video\]\[Enterprise\]](https://doitong.com/developers/models/openrouter/router/video/enterprise.md) (`openrouter/router/video/enterprise`): $0.01 / usage unit
- [OpenRouter \[Vision\]](https://doitong.com/developers/models/openrouter/router/vision.md) (`openrouter/router/vision`): $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/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=openrouter/router/video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/openrouter/router/video