OpenAI-compatible AI API gateway

InferGate

One endpoint.
More ways to build.

GPT-5.5, GPT-5.6 and GPT-6 through one familiar API.
Build with Python or Node.js. Stream responses. Stay in control of usage.

Get Started View Models

BASE URLhttps://api.useinfergate.com/v1

ONE API ENDPOINTSTREAMING RESPONSESPYTHON + NODE.JSPREPAID USAGE

The current lineup

Four models. Explicit choice.

Explore all models

Use the exact model you select. No silent substitutions.

Your authenticated model list determines account access. Availability and account limits apply.

From familiar SDK to first response

Keep your workflow.
Change your endpoint.

Your InferGate key, a model ID, and the SDK you already know. Start with a small request.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["INFERGATE_API_KEY"],
    base_url="https://api.useinfergate.com/v1",
)
response = client.responses.create(
    model="gpt-5.5",
    input="Reply with one sentence about API design.",
    max_output_tokens=256,
)
print(response.output_text)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.INFERGATE_API_KEY,
  baseURL: "https://api.useinfergate.com/v1",
});
const response = await client.responses.create({
  model: "gpt-5.5",
  input: "Reply with one sentence about API design.",
  max_output_tokens: 256,
});
console.log(response.output_text);

Python quickstart Node.js quickstart API documentation

Built around your application