# OpenRouter APIs — Runway: Aleph 2.0 (runway/aleph-2)

Guide for calling every confirmed OpenRouter API that serves `runway/aleph-2`.

Model page: https://openrouter.ai/runway/aleph-2
Create an API key: https://openrouter.ai/settings/keys

## Authentication

Send this header with every request:

- Authorization: Bearer $OPENROUTER_API_KEY

## Video API

Generate videos with `runway/aleph-2` through OpenRouter's Video API.

Docs: https://openrouter.ai/docs/guides/overview/multimodal/video-generation
Model discovery API: https://openrouter.ai/api/v1/videos/models

### Endpoint

POST https://openrouter.ai/api/v1/videos

Headers:
- Content-Type: application/json

Generation is asynchronous: the submit call returns a job, which is polled until it
finishes. The finished video is downloaded from the job, not returned inline.

### Request fields (runway/aleph-2)

- model: string (required) — `"runway/aleph-2"`
- prompt: string (required) — text description of the desired video
- aspect_ratio: "16:9" | "4:3" | "3:2" | "1:1" | "2:3" | "3:4" | "9:16" | "21:9" (optional) — aspect ratio of the generated video
- input_references: array of reference assets (optional) — images to guide the generation, as `{ "type": "image_url", "image_url": { "url": "…" } }` entries
- seed: integer (optional) — sample deterministically; determinism is not guaranteed for every provider
- callback_url: string (optional) — https URL notified by webhook when the job finishes, instead of polling

These are the generation parameters this model accepts between its providers; an unlisted
value is rejected, and a listed one can still be refused by whichever provider serves the
call. `provider` (routing preferences) is accepted on every request.

### Response

The submit call returns `202` with the job:

```json
{
  "id": "job-abc123",
  "generation_id": "gen-xyz789",
  "polling_url": "/api/v1/videos/job-abc123",
  "status": "pending"
}
```

Poll `GET https://openrouter.ai/api/v1/videos/{id}` with the same Authorization header while `status` is
`pending` or `in_progress`, and stop once it is `completed`, `failed`, `cancelled`, or
`expired`:

```json
{
  "id": "job-abc123",
  "status": "completed",
  "unsigned_urls": ["https://storage.example.com/video.mp4"],
  "usage": { "cost": 0.5 }
}
```

Download the bytes from `GET https://openrouter.ai/api/v1/videos/{id}/content` (`?index=N` selects a clip
when the job produced more than one). `usage.cost` is the USD charge for the call.

### Examples

#### Generate

```bash
curl -X POST https://openrouter.ai/api/v1/videos \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "runway/aleph-2",
  "prompt": "a slow cinematic push-in on a glowing neon sign that reads \"OpenRouter\" in the window of a cozy coffee shop on a rainy night, rain streaking down the glass, reflections rippling on wet pavement"
}'
```

### Error differences

- 404 also covers an unknown video job
- 500 — the job could not be submitted

A job that fails after acceptance reports `status: "failed"` with an `error` message rather than
an HTTP error, since the submit call already succeeded.

## Errors

Failures return `{"error": {"code": <number>, "message": <string>}}` with the HTTP status:

- 400 — malformed request or an unsupported parameter
- 401 — missing or invalid API key
- 402 — insufficient credits
- 403 — spend limit reached, key disabled, or access blocked
- 404 — unknown model or no provider can serve the request
- 429 — rate limited; retry with backoff
- 502 — the operation failed upstream; failed generations are not billed

---

Canonical version of this document: https://openrouter.ai/runway/aleph-2/llms.txt