> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Use Gemini Omni 1.2 Flash with Comfy Router

> Call gemini-interactions/gemini-omni-1.2-flash through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for `gemini-interactions/gemini-omni-1.2-flash`, served by Comfy Router from Gemini Interactions.

**Input:** Text, Image, Audio, Video · **Output:** Text + Video

## Quick start

Create a key in [your Comfy workspace](https://platform.comfy.org/profile/api-keys?onboarding=router) and export it as `COMFY_API_KEY`. The Python and TypeScript snippets use the Comfy SDKs (`pip install comfy-sdk` and `npm install @comfyorg/sdk`); the cURL snippet is the same call over raw HTTP.

**Model ID:** `gemini-interactions/gemini-omni-1.2-flash`

**Endpoint:** `POST https://api.comfy.org/v2/models/gemini-interactions/gemini-omni-1.2-flash`

> [tab] Wait for the result
>
> ```python Python theme={null}
> from comfy_sdk import Comfy
>
> # Reads COMFY_API_KEY from the environment.
> # The SDK automatically creates an idempotency key and reuses it for automatic retries.
> with Comfy() as client:
>     result = client.models.run(
>         "gemini-interactions/gemini-omni-1.2-flash",
>         {
>             "input": "Reply with the single word: ok",
>             "stream": False,
>         },
>     )
>
> print(result)
> ```
>
> ```typescript TypeScript theme={null}
> import { comfy } from "@comfyorg/sdk";
>
> // Reads COMFY_API_KEY from the environment.
> // The SDK automatically creates an idempotency key and reuses it for automatic retries.
> const { data } = await comfy.models.run("gemini-interactions/gemini-omni-1.2-flash", {
>   input: "Reply with the single word: ok",
>   stream: false,
> });
>
> console.log(data);
> ```
>
> ```bash cURL theme={null}
> curl https://api.comfy.org/v2/models/gemini-interactions/gemini-omni-1.2-flash \
>   -H "X-API-Key: $COMFY_API_KEY" \
>   -H "Idempotency-Key: $(uuidgen)" \
>   -H "Content-Type: application/json" \
>   -d "{\"input\": \"Reply with the single word: ok\", \"stream\": false}"
> ```

> [tab] Queue and collect later
>
> The same body, sent to `POST https://api.comfy.org/v2/models/gemini-interactions/gemini-omni-1.2-flash/requests`. Router answers `201` with a `request_id` as soon as the run is admitted, and the result is collected once it is ready, from this process or another one. [Queued delivery](https://docs.comfy.org/development/comfy-router/queue.md) walks through status, cancellation and collection.
>
> ```python Python theme={null}
> import asyncio
> from comfy_sdk import AsyncComfy
>
> # Reads COMFY_API_KEY from the environment.
> # Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
> async def main():
>     async with AsyncComfy() as client:
>         handle = await client.models.submit(
>             "gemini-interactions/gemini-omni-1.2-flash",
>             {
>                 "input": "Reply with the single word: ok",
>                 "stream": False,
>             },
>         )
>         print("request_id:", handle.request_id)  # with the model ID, all another process needs
>
>         # Poll until the request completes, waiting the Retry-After the server names.
>         async for update in handle.iter_events():
>             print(update.status, update.queue_position)
>
>         # The provider's own payload, the same value models.run() returns.
>         # A request that failed or was cancelled raises the typed Router error here.
>         result = await handle.get()
>
>     print(result)
>
> asyncio.run(main())
> ```
>
> ```typescript TypeScript theme={null}
> import { comfy } from "@comfyorg/sdk";
>
> // Reads COMFY_API_KEY from the environment.
> // Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
> const handle = await comfy.models.submit("gemini-interactions/gemini-omni-1.2-flash", {
>   input: "Reply with the single word: ok",
>   stream: false,
> });
> console.log("requestId:", handle.requestId); // with the model ID, all another process needs
>
> // Poll until the request completes, waiting the Retry-After the server names.
> for await (const update of handle.events()) {
>   console.log(update.status, update.queuePosition);
> }
>
> // The same result models.run() returns. A request that failed or was cancelled rejects here.
> const result = await handle.get();
>
> console.log(result.data);
> ```
>
> ```bash cURL theme={null}
> # 1. Submit. Router answers 201 with request_id, status_url, response_url and cancel_url.
> curl https://api.comfy.org/v2/models/gemini-interactions/gemini-omni-1.2-flash/requests \
>   -H "X-API-Key: $COMFY_API_KEY" \
>   -H "Idempotency-Key: $(uuidgen)" \
>   -H "Content-Type: application/json" \
>   -d "{\"input\": \"Reply with the single word: ok\", \"stream\": false}"
>
> # 2. Poll until status is COMPLETED, waiting the Retry-After seconds each response names.
> REQUEST_ID="<request_id from the 201 body>"
> curl -i https://api.comfy.org/v2/models/gemini-interactions/gemini-omni-1.2-flash/requests/$REQUEST_ID/status \
>   -H "X-API-Key: $COMFY_API_KEY"
>
> # 3. Collect. 200 with the model's native output, 202 with the status body while it is still running.
> curl https://api.comfy.org/v2/models/gemini-interactions/gemini-omni-1.2-flash/requests/$REQUEST_ID \
>   -H "X-API-Key: $COMFY_API_KEY"
> ```

## Schema

### Input

**input** `object` *required*

Either a prompt string or an array of typed content parts (text, image, audio, video, document).

**model** `string`

Gemini model identifier: `gemini-omni-1.2-flash` or `gemini-omni-1.1-flash` (generally available), or the deprecated `gemini-omni-flash-preview`. On the Comfy Router route `POST /v2/models/gemini-interactions/{model}` it is supplied from the path and may be omitted. Those three spellings — the set Comfy Router addresses as `gemini-interactions/<model>` — are the ones this operation serves (supportedGeminiInteractionModels); they are written out here rather than constrained to an enum, because the proxy validates the model itself and answers its own 400 for a spelling it does not serve.

**previous\_interaction\_id** `string`

ID of a prior stored interaction, enabling stateful multi-turn video editing.

Generated from the schema Router serves at `GET /v2/models/gemini-interactions/gemini-omni-1.2-flash/openapi.json`, the same document it validates a call against before the request reaches the provider.

### Output

**id** `string`

**model** `string`

**object** `string`

**status** `string` *required*

Always `completed` on a Router response. The provider's other statuses (`in_progress`, `requires_action`, `failed`, `cancelled`, `incomplete`, `budget_exceeded`) do not reach a caller through Router as a 200; they are returned as a Comfy Router error carrying the provider's body.

Possible values: `completed`

**steps** `object[]` *required*

The interaction timeline, in order. Narrowed here from the untyped `steps` on `GeminiInteraction` so the output leaf is addressable; the provider keeps adding step types, so an item is `additionalProperties: true` and only the fields a Router caller reads are declared.

**steps\[].content** `object[]`

The typed content blocks of this step.

**steps\[].content\[].data** `string`

Base64-encoded inline media, on a media block delivered inline. Google caps inline media at 4 MB and requires `delivery: uri` above it.

**steps\[].content\[].mime\_type** `string`

Media type of `data` or `uri`, on a media block.

**steps\[].content\[].text** `string`

The generated text. Present on a `text` block, and this is the leaf the nightly Router SDK case asserts — on a `model_output` step specifically (`steps[type=model_output].content[].text`).

**steps\[].content\[].type** `string`

Block kind — `text`, `image`, `audio`, `video` or `document`.

**steps\[].content\[].uri** `string`

Reference to media delivered out of band, fetched by the caller from the URI it names.

**steps\[].type** `string`

Step kind. `model_output` is the generated answer; `user_input` is the caller's own turn echoed back by the retrieval route; `thought` is internal reasoning. The tool steps (`function_call`, `function_result`, `code_execution_call`, `google_search_call`, ...) are open-ended and Google adds to them.

**usage** `object`

Token usage for a Gemini interaction.

**usage.input\_tokens\_by\_modality** `object[]`

Token count for one modality.

**usage.input\_tokens\_by\_modality\[].modality** `string`

One of `text`, `image`, `audio`, `video`, `document`.

**usage.input\_tokens\_by\_modality\[].tokens** `integer`

**usage.output\_tokens\_by\_modality** `object[]`

Token count for one modality.

**usage.output\_tokens\_by\_modality\[].modality** `string`

One of `text`, `image`, `audio`, `video`, `document`.

**usage.output\_tokens\_by\_modality\[].tokens** `integer`

**usage.total\_cached\_tokens** `integer`

**usage.total\_input\_tokens** `integer`

**usage.total\_output\_tokens** `integer`

**usage.total\_thought\_tokens** `integer`

**usage.total\_tokens** `integer`

## Examples

### Input

```json theme={null}
{
  "input": "Reply with the single word: ok",
  "stream": false
}
```

### Output

```json theme={null}
{
  "id": "interactions/3f6c1a90-2b47-4d18-9a55-7c0e8b21d4f3",
  "object": "interaction",
  "status": "completed",
  "steps": [
    {
      "content": [
        {
          "text": "ok",
          "type": "text"
        }
      ],
      "type": "model_output"
    }
  ],
  "usage": {
    "input_tokens_by_modality": [
      {
        "modality": "text",
        "tokens": 9
      }
    ],
    "output_tokens_by_modality": [
      {
        "modality": "text",
        "tokens": 2
      }
    ],
    "total_cached_tokens": 0,
    "total_input_tokens": 9,
    "total_output_tokens": 2,
    "total_thought_tokens": 0,
    "total_tokens": 11
  }
}
```

## Before you ship

The SDKs create an `Idempotency-Key` and reuse it for automatic retries. For manual retries, reuse the original key. Router can hold the connection for up to 10 minutes.

When a request fails, Router sends an `X-Comfy-Error-Type` response header explaining why. A `422` means Router rejected the input before calling the provider, and a `413` means the request body was larger than Router accepts. Download generated assets promptly because [result URLs can expire](https://docs.comfy.org/development/comfy-router/reference.md#result-assets).

Any size limit named in a field description above is the provider's own bound on that field, quoted from the provider's specification. Router applies a separate cap to the whole request body, which base64-encoded media counts against: see [request body size](https://docs.comfy.org/development/comfy-router/limitations.md#request-bodies-are-capped).

This page documents one partner model called through Comfy Router. The same `comfy-sdk` / `@comfyorg/sdk` package also ships a second client, for running a whole ComfyUI workflow graph on Comfy Cloud: `Comfy(api_key=...)` / `new Comfy({ apiKey })`, with `client.workflows`, `client.assets` and `client.jobs`. See [Comfy SDKs](https://docs.comfy.org/development/api-development/sdks.md).

> [card] [Headers](https://docs.comfy.org/development/comfy-router/headers.md)
>
> Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.

> [card] [Using the Router API](https://docs.comfy.org/development/comfy-router/api.md)
>
> Model discovery, validation errors, retries, and billing.

> [card] [Limitations](https://docs.comfy.org/development/comfy-router/limitations.md)
>
> What Router does not do today, and what to use instead.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.