> ## 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 Flash Preview with Comfy Router

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

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

## Quick start

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

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

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

<CodeGroup>
  ```python Python theme={null}
  from comfy_sdk import Comfy

  # Reads COMFY_API_KEY from the environment. Each call sends a fresh
  # Idempotency-Key and waits up to 10 minutes for the finished result.
  with Comfy() as client:
      result = client.models.run(
          "gemini-interactions/gemini-omni-flash-preview",
          {
              # Request fields are the provider's own — see Input below.
          },
      )

  print(result)
  ```

  ```typescript TypeScript theme={null}
  import { comfy } from "@comfyorg/sdk";

  // Reads COMFY_API_KEY from the environment. Each call sends a fresh
  // Idempotency-Key and waits up to 10 minutes for the finished result.
  const { data } = await comfy.models.run("gemini-interactions/gemini-omni-flash-preview", {
    // Request fields are the provider's own — see Input below.
  });

  console.log(data);
  ```

  ```bash cURL theme={null}
  # Request fields are the provider's own — see Input below.
  curl https://api.comfy.org/v2/models/gemini-interactions/gemini-omni-flash-preview \
    -H "X-API-Key: $COMFY_API_KEY" \
    -H "Idempotency-Key: $(uuidgen)" \
    -H "Content-Type: application/json" \
    -d '{}'
  ```
</CodeGroup>

## Schema

### Input

<Note>
  Router has not published an authored input schema for this model yet: `GET /v2/models/gemini-interactions/gemini-omni-flash-preview/openapi.json` returns an open object with `x-comfy-input-schema-authored: false`. Router forwards the body to Gemini Interactions unchanged, so [Gemini Interactions's own API reference](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference) is authoritative for the request fields, and nothing is validated server side.
</Note>

### Output

<ResponseField name="id" type="string" />

<ResponseField name="model" type="string" />

<ResponseField name="object" type="string" />

<ResponseField name="status" type="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`
</ResponseField>

<ResponseField name="steps" type="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.
</ResponseField>

<ResponseField name="steps[].content" type="object[]">
  The typed content blocks of this step.
</ResponseField>

<ResponseField name="steps[].content[].data" type="string">
  Base64-encoded inline media, on a media block delivered inline. Google caps inline media at 4 MB and requires `delivery: uri` above it.
</ResponseField>

<ResponseField name="steps[].content[].mime_type" type="string">
  Media type of `data` or `uri`, on a media block.
</ResponseField>

<ResponseField name="steps[].content[].text" type="string">
  The generated text. Present on a `text` block, and this is the leaf the nightly Router SDK case asserts (`steps[].content[].text`).
</ResponseField>

<ResponseField name="steps[].content[].type" type="string">
  Block kind — `text`, `image`, `audio`, `video` or `document`.
</ResponseField>

<ResponseField name="steps[].content[].uri" type="string">
  Reference to media delivered out of band, fetched by the caller from the URI it names.
</ResponseField>

<ResponseField name="steps[].type" 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.
</ResponseField>

<ResponseField name="usage" type="object">
  Token usage for a Gemini interaction.
</ResponseField>

<ResponseField name="usage.input_tokens_by_modality" type="object[]">
  Token count for one modality.
</ResponseField>

<ResponseField name="usage.input_tokens_by_modality[].modality" type="string">
  One of `text`, `image`, `audio`, `video`, `document`.
</ResponseField>

<ResponseField name="usage.input_tokens_by_modality[].tokens" type="integer" />

<ResponseField name="usage.output_tokens_by_modality" type="object[]">
  Token count for one modality.
</ResponseField>

<ResponseField name="usage.output_tokens_by_modality[].modality" type="string">
  One of `text`, `image`, `audio`, `video`, `document`.
</ResponseField>

<ResponseField name="usage.output_tokens_by_modality[].tokens" type="integer" />

<ResponseField name="usage.total_cached_tokens" type="integer" />

<ResponseField name="usage.total_input_tokens" type="integer" />

<ResponseField name="usage.total_output_tokens" type="integer" />

<ResponseField name="usage.total_thought_tokens" type="integer" />

<ResponseField name="usage.total_tokens" type="integer" />

## Examples

### 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 snippets above are the shortest working call. Three things are the same for every model and are documented once on the [Comfy Router headers](/development/comfy-router/headers) page: send an `Idempotency-Key` on every paid call and reuse it when you retry, expect the connection to be held up to Router's 10 minute deadline, and keep `X-Comfy-Request-Id` from every response. The SDKs do all three for you; the cURL tab does none of them. On failure, `X-Comfy-Error-Type` names the bucket, and a `422` means the body failed the model's schema and was never billed.

<CardGroup cols={3}>
  <Card title="Headers" icon="list" href="/development/comfy-router/headers">
    Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.
  </Card>

  <Card title="Quick Start" icon="rocket" href="/development/comfy-router/quickstart">
    Typed error handling in Python and TypeScript, reading the 422, walking the catalog.
  </Card>

  <Card title="Limitations" icon="triangle-exclamation" href="/development/comfy-router/limitations">
    What Router does not do today, and what to use instead.
  </Card>
</CardGroup>