Use GPT Image 2 with Comfy Router

Use openai/gpt-image-2 with the Comfy Router API. OpenAI provides the model; Router gives it the shared authentication and request route below.

Quick start

Create a key at 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

import uuid
from comfy_sdk import Comfy

# Reads COMFY_API_KEY from the environment. Save this key and reuse it if you
# retry this request after the SDK returns an error.
idempotency_key = str(uuid.uuid4())
with Comfy() as client:
    result = client.models.run(
        "openai/gpt-image-2",
        {
            # Request fields are the provider's own — see Input below.
        },
        idempotency_key=idempotency_key,
    )

print(result)

import { comfy } from "@comfyorg/sdk";

// Reads COMFY_API_KEY from the environment. Save this key and reuse it if you
// retry this request after the SDK returns an error.
const idempotencyKey = crypto.randomUUID();
const { data } = await comfy.models.run("openai/gpt-image-2", {
  // Request fields are the provider's own — see Input below.
}, { idempotencyKey });

console.log(data);

# Request fields are the provider's own — see Input below.
# Run this line once. Reuse ROUTER_REQUEST_KEY if you retry the curl command.
ROUTER_REQUEST_KEY=$(uuidgen)
curl https://api.comfy.org/v2/models/openai/gpt-image-2 \
  -H "X-API-Key: $COMFY_API_KEY" \
  -H "Idempotency-Key: $ROUTER_REQUEST_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

Schema

Input

string

Background transparencyPossible values: transparent, opaque

string

The model to use for image generation (e.g., gpt-image-1, gpt-image-1.5, gpt-image-2)

string

Content moderation settingPossible values: low, auto

integer

The number of images to generate (1-10).

integer

Compression level for JPEG or WebP (0-100)

string

Format of the output imagePossible values: png, webp, jpeg

string

required

A text description of the desired image

string

The quality of the generated imagePossible values: low, medium, high, standard, hd

string

Response format of image dataPossible values: url, b64_json

string

Size of the image (e.g., 1024x1024, 1536x1024, auto)

string

Style of the image. Unused by the gpt-image models this operation admits; it was a dall-e-3-only parameter and those ids were retired when OpenAI shut them down on 2026-05-12.Possible values: vivid, natural

string

A unique identifier for end-user monitoring

Generated from the schema Router serves at GET /v2/models/openai/gpt-image-2/openapi.json, the same document it validates a call against before the request reaches the provider.

Output

object[]

string

Base64 encoded image data

string

Revised prompt

string

URL of the image

object

integer

object

integer

object

integer

string

Whether the generated image’s background is opaque or transparent. Populated on the fal-served branch only, which reports opaque.

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

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.

string

The quality tier the generation actually ran at. Populated on the fal-served branch when it can resolve one; absent otherwise.

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.

Examples

Input

{
  "n": 1,
  "prompt": "a red circle",
  "quality": "low",
  "size": "1024x1024"
}

Output

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

Before you ship

Save one Idempotency-Key for each call and reuse it for retries. Router can hold the connection for up to 10 minutes. The SDKs handle authentication; raw HTTP clients send the headers themselves. Use X-Comfy-Error-Type to classify a failure. A 422 means Router rejected the input before calling the provider. Download generated assets promptly because result URLs can expire.

Headers

Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.

Using the Router API

Find models, inspect schemas, and retry safely.

Limitations

What Router does not do today, and what to use instead.

Develop with Comfy

Deploy ComfyUI

Run Workflows

Comfy Router

Comfy CLI

Specifications

Use GPT Image 2 with Comfy Router

Quick start

Schema

Input

Output

Examples

Input

Output

Before you ship

Headers

Using the Router API

Limitations

​Quick start

​Schema

​Input

​Output

​Examples

​Input

​Output

​Before you ship

Headers

Using the Router API

Limitations

Quick start

Schema

Input

Output

Examples

Input

Output

Before you ship