> ## 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 GPT Image 2 with Comfy Router

> Call openai/gpt-image-2 through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for `openai/gpt-image-2`, served by Comfy Router from OpenAI.

## 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:** `openai/gpt-image-2`

**Endpoint:** `POST https://api.comfy.org/v2/models/openai/gpt-image-2`

<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(
          "openai/gpt-image-2",
          {
              # 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("openai/gpt-image-2", {
    // 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/openai/gpt-image-2 \
    -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/openai/gpt-image-2/openapi.json` returns an open object with `x-comfy-input-schema-authored: false`. Router forwards the body to OpenAI unchanged, so [OpenAI's own API reference](https://platform.openai.com/docs/api-reference) is authoritative for the request fields, and nothing is validated server side.
</Note>

### Output

<ResponseField name="data" type="object[]" />

<ResponseField name="data[].b64_json" type="string">
  Base64 encoded image data
</ResponseField>

<ResponseField name="data[].revised_prompt" type="string">
  Revised prompt
</ResponseField>

<ResponseField name="data[].url" type="string">
  URL of the image
</ResponseField>

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

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

<ResponseField name="usage.input_tokens_details" type="object" />

<ResponseField name="usage.input_tokens_details.image_tokens" type="integer" />

<ResponseField name="usage.input_tokens_details.text_tokens" type="integer" />

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

<ResponseField name="usage.output_tokens_details" type="object" />

<ResponseField name="usage.output_tokens_details.image_tokens" type="integer" />

<ResponseField name="usage.output_tokens_details.text_tokens" type="integer" />

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

<ResponseField name="background" type="string">
  Whether the generated image's background is opaque or transparent. Populated on the fal-served branch only, which reports `opaque`.
</ResponseField>

<ResponseField name="created" type="integer">
  Unix timestamp, in seconds, of when the generation completed. Declared `int64` because a present-day epoch value is close enough to 2^31 that an unformatted `integer` generates a 32-bit field in many SDK generators.

  Format: `int64`
</ResponseField>

<ResponseField name="output_format" type="string">
  The encoding of the bytes in `data[].b64_json` (for example `png`). Populated on the fal-served branch; absent on the OpenAI-served one, where the caller's requested `output_format` is authoritative.
</ResponseField>

<ResponseField name="quality" type="string">
  The quality tier the generation actually ran at. Populated on the fal-served branch when it can resolve one; absent otherwise.
</ResponseField>

<ResponseField name="size" type="string">
  The pixel dimensions the generation actually ran at, as `<width>x<height>`. Populated on the fal-served branch when it can resolve one; absent otherwise.
</ResponseField>

## Examples

### Output

```json theme={null}
{
  "created": 1767225600,
  "data": [
    {
      "b64_json": "PGJhc2U2ND4="
    }
  ],
  "usage": {
    "input_tokens": 12,
    "output_tokens": 1056,
    "total_tokens": 1068
  }
}
```

## 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>