Use GPT Image 1.5 with Comfy Router

Call openai/gpt-image-1.5 through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for openai/gpt-image-1.5, served by Comfy Router from OpenAI.

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-1.5

Endpoint: POST https://api.comfy.org/v2/models/openai/gpt-image-1.5

Python

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-1.5",
        {
            "n": 1,
            "prompt": "a red circle",
            "quality": "low",
            "size": "1024x1024",
        },
    )

print(result)

Schema

Input

background · string

Background transparency

Possible values: transparent, opaque

model · string

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

moderation · string

Content moderation setting

Possible values: low, auto

n · integer

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

output_compression · integer

Compression level for JPEG or WebP (0-100)

output_format · string

Format of the output image

Possible values: png, webp, jpeg

prompt · string · required

A text description of the desired image

quality · string

The quality of the generated image

Possible values: low, medium, high, standard, hd

response_format · string

Response format of image data

Possible values: url, b64_json

size · string

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

style · 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

user · string

A unique identifier for end-user monitoring

Generated from the schema Router serves at GET /v2/models/openai/gpt-image-1.5/openapi.json, the same document it validates a call against before the request reaches the provider.

Output

data · object[]

data[].b64_json · string

Base64 encoded image data

data[].revised_prompt · string

Revised prompt

data[].url · string

URL of the image

usage · object

usage.input_tokens · integer

usage.input_tokens_details · object

usage.input_tokens_details.image_tokens · integer

usage.input_tokens_details.text_tokens · integer

usage.output_tokens · integer

usage.output_tokens_details · object

usage.output_tokens_details.image_tokens · integer

usage.output_tokens_details.text_tokens · integer

usage.total_tokens · integer

background · string

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

created · 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

output_format · 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.

quality · string

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

size · 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

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 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.

Headers

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

Quick Start

Typed error handling in Python and TypeScript, reading the 422, walking the catalog.

Limitations

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