Use GPT 5 Mini with Comfy Router

API Reference for openai/gpt-5-mini, 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-5-mini Endpoint: POST https://api.comfy.org/v2/models/openai/gpt-5-mini

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-5-mini",
        {
            # Request fields are the provider's own — see Input below.
        },
    )

print(result)

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-5-mini", {
  // Request fields are the provider's own — see Input below.
});

console.log(data);

# Request fields are the provider's own — see Input below.
curl https://api.comfy.org/v2/models/openai/gpt-5-mini \
  -H "X-API-Key: $COMFY_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d '{}'

Schema

Input

Router has not published an authored input schema for this model yet: GET /v2/models/openai/gpt-5-mini/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 is authoritative for the request fields, and nothing is validated server side.

Output

string

Inserts a system (or developer) message as the first item in the model’s context.When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

integer

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

string

The model used to generate the response

number

default:"1"

Controls randomness in the responseRange: 0 to 2

number

default:"1"

Controls diversity of the response via nucleus samplingRange: 0 to 1

string

default:"\"disabled\""

The truncation strategy to use for the model response.

auto: If the context of this response and previous ones exceeds the model’s context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation.
disabled (default): If a model response will exceed the context window size for a model, the request will fail with a 400 error. Possible values: auto, disabled

string

The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state.

object

o-series models onlyConfiguration options for reasoning models.

string

Controls which reasoning items are rendered back to the model on later turns, e.g. auto, current_turn, or all_turns.

string

default:"\"medium\""

o-series models onlyConstrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.Possible values: low, medium, high

string

Deprecated: use summary instead.A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model’s reasoning process. One of auto, concise, or detailed.Possible values: auto, concise, detailed

string

The reasoning mode used for the response.

string

A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model’s reasoning process. One of auto, concise, or detailed.Possible values: auto, concise, detailed

object

object | object | object

An object specifying the format that the model must output.Configuring { "type": "json_schema" } enables Structured Outputs, which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.The default format is { "type": "text" } with no additional options.Not recommended for gpt-4o and newer models:Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

string

Constrains the verbosity of the model’s response. One of low, medium, or high.

`none`, `auto`, `required` | object | object

How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.

object | object | object | object[]

boolean

Whether the model response runs in the background.

object

Billing information for the response.

string

The party responsible for paying for the response.

number

Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.

number

Unix timestamp (in seconds) of when this Response was created.

object

An error object returned when the model fails to generate a Response.

string

required

The error code for the response.Possible values: server_error, rate_limit_exceeded, invalid_prompt, vector_store_timeout, invalid_image, invalid_image_format, invalid_base64_image, invalid_image_url, image_too_large, image_too_small, image_parse_error, image_content_policy_violation, invalid_image_mode, image_file_too_large, unsupported_image_media_type, empty_image_file, failed_to_download_image, image_file_not_found

string

required

A human-readable description of the error.

number

Penalizes new tokens based on their existing frequency in the text so far.

string

Unique identifier for this Response.

object

Details about why the response is incomplete.

string

The reason why the response is incomplete.Possible values: max_output_tokens, content_filter

integer

The maximum number of total calls to built-in tools that can be processed in a response.

object

Set of key-value pairs that can be attached to the response.

object

Moderation results for the response input and output, if moderated completions were requested.

string

The object type of this resource - always set to response.Possible values: response

An array of content items generated by the model.

The length and order of items in the output array is dependent on the model’s response.
Rather than accessing the first item in the output array and assuming it’s an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.

string

SDK-only convenience property that contains the aggregated text output from all output_text items in the output array, if any are present. Supported in the Python and JavaScript SDKs.

boolean

default:"true"

Whether to allow the model to run tool calls in parallel.

number

Penalizes new tokens based on whether they appear in the text so far.

string

Used by OpenAI to cache responses for similar requests to optimize cache hit rates. Replaces the user field.

string

The retention policy for the prompt cache, e.g. in_memory or 24h.

string

A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies.

string

The processing tier used to serve the request, e.g. auto, default, flex, scale, or priority.

string

The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.Possible values: completed, failed, in_progress, cancelled, queued, incomplete

boolean

Whether the response is stored for later retrieval via the API.

object

Token and request usage broken down by built-in tool.

object

Image generation tool token usage.

integer

object

integer

object

integer

object

Web search tool usage.

integer

The maximum number of most likely tokens to return at each token position, each with an associated log probability.

object

Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.

integer

required

The number of input tokens.

object

required

A detailed breakdown of the input tokens.

integer

The number of input tokens that were written to the cache.

integer

required

The number of tokens that were retrieved from the cache. More on prompt caching.

integer

required

The number of output tokens.

object

required

A detailed breakdown of the output tokens.

integer

required

The number of reasoning tokens.

integer

required

The total number of tokens used.

string

Deprecated identifier for the end-user. Replaced by safety_identifier and prompt_cache_key.

Examples

Output

{
  "completed_at": 1767225601,
  "created_at": 1767225600,
  "id": "resp_0a1b2c3d4e5f6a7b8c9d0e1f",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "text": "ok",
          "type": "output_text"
        }
      ],
      "id": "msg_0a1b2c3d4e5f6a7b8c9d0e1f",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "output_text": "ok",
  "status": "completed",
  "usage": {
    "input_tokens": 14,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 2,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 16
  }
}

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.

Develop with Comfy

Deploy ComfyUI

Run Workflows

Comfy Router

Comfy CLI

Specifications

Use GPT 5 Mini with Comfy Router

Quick start

Schema

Input

Output

Examples

Output

Before you ship

Headers

Quick Start

Limitations

​Quick start

​Schema

​Input

​Output

​Examples

​Output

​Before you ship

Headers

Quick Start

Limitations

Quick start

Schema

Input

Output

Examples

Output

Before you ship