Use Google Gemini with Comfy Router

Python, TypeScript and cURL snippets for calling Google Gemini text models over HTTP through Comfy Router, plus the request fields and the result shape

API Reference for Google Gemini. Google Gemini is Google’s family of multimodal text models, covering fast drafting through deep reasoning across the Flash and Pro tiers.

Comfy Router is not generally available yet. POST /v2/models/{provider}/{model} and its catalog and schema siblings are not serving requests yet: an authenticated call answers 404 today. The snippets on this page document the contract those routes will serve, published ahead of the rollout so your integration is ready to write against.

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.

Pick the model you want to call. The models share one request and response shape, documented once below.

Gemini 3.1 Pro

Model ID: vertexai/gemini-3.1-pro-preview

Endpoint: POST https://api.comfy.org/v2/models/vertexai/gemini-3.1-pro-preview

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(
        "vertexai/gemini-3.1-pro-preview",
        {
            "contents": [
                {
                    "role": "user",
                    "parts": [
                        {
                            "text": "Describe a single red maple leaf on a white background in one sentence.",
                        },
                    ],
                },
            ],
            "generationConfig": {
                "temperature": 0.7,
                "maxOutputTokens": 256,
            },
        },
    )

print("text:", result["candidates"][0]["content"]["parts"][0]["text"])

Gemini 3.5 Flash

Model ID: vertexai/gemini-3.5-flash

Endpoint: POST https://api.comfy.org/v2/models/vertexai/gemini-3.5-flash

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(
        "vertexai/gemini-3.5-flash",
        {
            "contents": [
                {
                    "role": "user",
                    "parts": [
                        {
                            "text": "Describe a single red maple leaf on a white background in one sentence.",
                        },
                    ],
                },
            ],
            "generationConfig": {
                "temperature": 0.7,
                "maxOutputTokens": 256,
            },
        },
    )

print("text:", result["candidates"][0]["content"]["parts"][0]["text"])

Gemini 2.5 Pro

Model ID: vertexai/gemini-2.5-pro

Endpoint: POST https://api.comfy.org/v2/models/vertexai/gemini-2.5-pro

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(
        "vertexai/gemini-2.5-pro",
        {
            "contents": [
                {
                    "role": "user",
                    "parts": [
                        {
                            "text": "Describe a single red maple leaf on a white background in one sentence.",
                        },
                    ],
                },
            ],
            "generationConfig": {
                "temperature": 0.7,
                "maxOutputTokens": 256,
            },
        },
    )

print("text:", result["candidates"][0]["content"]["parts"][0]["text"])

Gemini 2.5 Flash

Model ID: vertexai/gemini-2.5-flash

Endpoint: POST https://api.comfy.org/v2/models/vertexai/gemini-2.5-flash

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(
        "vertexai/gemini-2.5-flash",
        {
            "contents": [
                {
                    "role": "user",
                    "parts": [
                        {
                            "text": "Describe a single red maple leaf on a white background in one sentence.",
                        },
                    ],
                },
            ],
            "generationConfig": {
                "temperature": 0.7,
                "maxOutputTokens": 256,
            },
        },
    )

print("text:", result["candidates"][0]["content"]["parts"][0]["text"])

Schema

Input

Fields follow Google’s published API specification and are checked against it in CI. Router’s own schema for this model is not published yet, so requests are forwarded to the provider unvalidated.

contents · object[] · required

The conversation so far, oldest first. A part is text, or inlineData to send an image, audio or video alongside the prompt.

contents[].role · string · required

Who authored the turn.

Possible values: user, model

contents[].parts · object[] · required

The turn’s content parts.

contents[].parts[].text · string

A text part.

contents[].parts[].inlineData · object

An inline media part.

contents[].parts[].inlineData.mimeType · string

Media type, for example image/png.

contents[].parts[].inlineData.data · string

Base64-encoded media bytes.

systemInstruction · object

System prompt applied to the whole conversation.

systemInstruction.parts · object[]

systemInstruction.parts[].text · string

generationConfig · object

Sampling and length settings.

generationConfig.temperature · number

Randomness of sampling. Defaults are model specific.

Range: 0 to 2

generationConfig.topP · number

Nucleus sampling threshold. Defaults are model specific.

generationConfig.topK · integer

Top-k sampling cutoff. Defaults are model specific.

generationConfig.maxOutputTokens · integer

Upper bound on generated tokens.

generationConfig.seed · integer

Seed for reproducible sampling.

generationConfig.stopSequences · string[]

Strings that end generation when produced.

generationConfig.thinkingConfig · object

Reasoning effort controls on models that support it.

generationConfig.thinkingConfig.thinkingLevel · string

Possible values: MINIMAL, LOW, MEDIUM, HIGH

generationConfig.thinkingConfig.includeThoughts · boolean

Return the model’s reasoning alongside the answer.

tools · object[]

Function declarations the model may call.

tools[].functionDeclarations · object[]

tools[].functionDeclarations[].name · string

tools[].functionDeclarations[].description · string

tools[].functionDeclarations[].parameters · object

JSON Schema for the function’s arguments.

Output

Router returns Google’s native response unchanged. The text is at candidates[0].content.parts[0].text.

candidates · object[]

Generated candidates; one unless you asked for more.

candidates[].content · object

candidates[].content.role · string

Possible values: model

candidates[].content.parts · object[]

candidates[].content.parts[].text · string

The generated text.

candidates[].content.parts[].functionCall · object

Present when the model chose to call one of your tools.

candidates[].content.parts[].functionCall.name · string

candidates[].content.parts[].functionCall.args · object

candidates[].finishReason · string

Why generation stopped: STOP, MAX_TOKENS, SAFETY, …

usageMetadata · object

Token accounting for the call.

usageMetadata.promptTokenCount · integer

Tokens in the prompt.

usageMetadata.candidatesTokenCount · integer

Tokens in the generated candidates.

promptFeedback · object

Present when the prompt itself was blocked. It is the only field returned in that case, so check for it before reading the result.

promptFeedback.blockReason · string

Why the prompt was blocked. No candidates are returned; rephrase the prompt and retry.

Possible values: SAFETY, OTHER, BLOCKLIST, PROHIBITED_CONTENT, IMAGE_SAFETY

Examples

Input

{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Describe a single red maple leaf on a white background in one sentence."
        }
      ]
    }
  ],
  "generationConfig": {
    "temperature": 0.7,
    "maxOutputTokens": 256
  }
}

Output

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "A single red maple leaf rests on a plain white background, its edges sharp and its color deep."
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 18,
    "candidatesTokenCount": 24
  }
}

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.

Quickstart

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.