# OpenRouter APIs — Google: Gemini Omni 1.2 Flash (google/gemini-omni-1.2-flash)

Guide for calling every confirmed OpenRouter API that serves `google/gemini-omni-1.2-flash`.

Model page: https://openrouter.ai/google/gemini-omni-1.2-flash
Create an API key: https://openrouter.ai/settings/keys

## Pricing

Standard-variant prices for `google/gemini-omni-1.2-flash`, per provider, in the unit each provider bills (tokens, images, seconds of video, or characters of audio). Pay-as-you-go with no markup on the provider's price.

- Google AI Studio: $1.50/M tokens input, $9/M tokens output (plus 1 more; see the model page for the full price list)

Full price table, including other variants and per-request charges: https://openrouter.ai/google/gemini-omni-1.2-flash
How OpenRouter prices requests: https://openrouter.ai/pricing

## EU in-region routing

`google/gemini-omni-1.2-flash` is not currently available through EU in-region routing.

Docs: https://openrouter.ai/docs/guides/features/in-region-routing

## Authentication

Send this header with every request:

- Authorization: Bearer $OPENROUTER_API_KEY

## Text / Chat Completions API

Generate text with `google/gemini-omni-1.2-flash` through OpenRouter's Chat Completions API.

Docs: https://openrouter.ai/docs/api/api-reference/chat/create-a-chat-completion

### Endpoint

POST https://openrouter.ai/api/v1/chat/completions

Headers:
- Content-Type: application/json

### Request fields (google/gemini-omni-1.2-flash)

- model: string (required) — `"google/gemini-omni-1.2-flash"`
- messages: array (required) — ordered conversation messages with `role` and `content`
- stream: boolean (optional) — return Server-Sent Events as tokens are generated
- max_tokens: optional — accepted by this model; see the API reference for its value shape
- reasoning: optional — accepted by this model; see the API reference for its value shape
- reasoning_effort: optional — accepted by this model; see the API reference for its value shape
- seed: optional — accepted by this model; see the API reference for its value shape
- temperature: optional — accepted by this model; see the API reference for its value shape
- top_p: optional — accepted by this model; see the API reference for its value shape

The model-specific optional fields above come from this model's advertised capabilities.
`stream` and `provider` routing preferences are API controls accepted independently of that
model capability list.

### Response

Without `stream`, the response is a Chat Completions JSON object:

```json
{
  "id": "gen-abc123",
  "choices": [{ "message": { "role": "assistant", "content": "..." } }],
  "usage": { "prompt_tokens": 12, "completion_tokens": 24, "total_tokens": 36, "cost": 0.001 }
}
```

With `stream: true`, the response is `text/event-stream`: read each `data:` JSON chunk until
`data: [DONE]`. The final usage chunk carries token counts and cost when usage is requested.

### Examples

#### Chat completion

```bash
curl -X POST https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/gemini-omni-1.2-flash",
  "messages": [
    {
      "role": "user",
      "content": "What is the meaning of life?"
    }
  ]
}'
```

### Error differences

- 400 — malformed messages or a parameter this model does not support
- 502 — the upstream text generation failed

## Video API

Generate videos with `google/gemini-omni-1.2-flash` 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 (google/gemini-omni-1.2-flash)

- model: string (required) — `"google/gemini-omni-1.2-flash"`
- prompt: string (optional when frame_images is set, otherwise required) — text description of the desired video
- duration: 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 (optional) — length of the video in seconds
- size: "1280x720" | "720x1280" | "1920x1080" | "1080x1920" | "3840x2160" | "2160x3840" | "640x360" | "360x640" (optional) — exact pixel dimensions, as WIDTHxHEIGHT
- resolution: "720p" | "1080p" | "4K" | "360p" (optional) — resolution tier; interchangeable with size when paired with aspect_ratio
- aspect_ratio: "16:9" | "9:16" (optional) — aspect ratio of the generated video
- frame_images: array of frame references (optional) — images to condition the named frame on, as `{ "type": "image_url", "image_url": { "url": "…" }, "frame_type": "first_frame" }` entries; frame_type is one of "first_frame" | "last_frame", and the url is an https URL or a base64 data URL
- input_references: array of reference assets (optional) — images to guide the generation, as `{ "type": "image_url", "image_url": { "url": "…" } }` entries
- generate_audio: boolean (optional) — generate audio alongside the video
- 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

#### Text to Video

```bash
curl -X POST https://openrouter.ai/api/v1/videos \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/gemini-omni-1.2-flash",
  "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",
  "duration": 5,
  "aspect_ratio": "16:9"
}'
```

### 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/google/gemini-omni-1.2-flash/llms.txt