API quickstart

The Inference.net API is OpenAI-compatible, so you can use the OpenAI SDK or plain HTTP to make requests. There are two ways to use it:

1. Call a model serverless: call open-source models and popular closed-source models (GPT, Claude, Gemini) with just your Inference.net API key. Usage is billed per token to your credit balance.
2. Proxy through the Inference.net Gateway: route requests to any provider (OpenAI, Anthropic, etc.) through the Inference.net Gateway with your own provider API key.

Both paths use the same base URL and the same Inference.net API key.

#Get an API key

1. Create an account

   Create an account at /register, or sign in with an existing account.

2. Create an API key

   Open API keys in the dashboard. Create a new key.

3. Set the environment variable

   bash

   export INFERENCE_API_KEY=<your-api-key>

#1. Call a model serverless

Call models with just your Inference.net API key. No provider API key is needed. This works for two kinds of models:

• Open-source models hosted on Inference.net, such as glm-5.2.
• Popular closed-source models, such as claude-haiku-4-5, gpt-5-mini, and gemini-3.5-flash. Inference.net routes the request to the provider for you and bills the usage per token to your credit balance.

Browse available models in the model catalog, or list them with GET https://api.inference.net/v1/models.

Some models are privileged. They have "requires_approved_access": true in GET /v1/models, and your team must be approved before it can call them. See Privileged model access.

For US-only inference, use https://us.api.inference.net/v1: same API and same models, but requests are handled by US data centers end to end: US Cloudflare edge, US routing, and US-hosted GPU capacity.

Prefer the Anthropic SDK? The API also supports the Anthropic Messages format. See Anthropic SDK.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inference.net/v1",
  apiKey: process.env.INFERENCE_API_KEY,
});

const response = await client.chat.completions.create({
  model: "glm-5.2",
  messages: [{ role: "user", content: "What is the meaning of life?" }],
  stream: true,
});

for await (const chunk of response) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

The same code works for every serverless model. Set model to the model ID you want, for example claude-haiku-4-5. This includes the purpose-built Schematron models for structured data extraction.

#2. Proxy through the Inference.net Gateway

Route requests to any LLM provider (OpenAI, Anthropic, Groq, etc.) through the Inference.net Gateway. You keep your existing provider API key, and the provider bills you directly. The gateway adds roughly 10ms of latency.

Use this path when you want a model that is not in the serverless catalog, or when you want usage billed to your own provider account.

Your Inference.net API key authenticates with the gateway. Your provider API key is forwarded to the provider via the x-inference-provider-api-key header.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inference.net/v1",
  apiKey: process.env.INFERENCE_API_KEY,
  defaultHeaders: {
    "x-inference-provider-api-key": process.env.OPENAI_API_KEY,
    "x-inference-provider": "openai",
  },
});

const response = await client.chat.completions.create({
  model: "gpt-4.1",
  messages: [{ role: "user", content: "What is the meaning of life?" }],
});

console.log(response.choices[0].message.content);

#Headers reference

#Supported request parameters

The API supports the standard OpenAI chat completions parameters:

#Next steps