Chat Completion API

Guide to FastRouter's OpenAI-compatible Chat Completion endpoint, including SDK and direct API examples in Python, TypeScript, Curl, and JavaScript for seamless LLM interactions.

Introduction

FastRouter provides an OpenAI-compatible endpoint that lets you interact with a wide range of large language models (LLMs) using familiar schemas and SDKs. This makes it simple to generate text, answer questions, build conversational agents, or integrate LLMs into your applications — with zero vendor lock-in.

Whether you're using the OpenAI SDK or making direct HTTP calls, FastRouter routes your requests intelligently and efficiently, with full support for streaming.

Before you begin, replace placeholders like <FASTROUTER_API_KEY> with your actual API key, available in your dashboard (see Keys & Settings docs).

OpenAI-Compatible Chat Request Format

FastRouter uses the same schema as OpenAI’s /v1/chat/completions endpoint. You can specify models from multiple providers, such as:

openai/gpt-5.1
google/gemini-3-pro-preview
anthropic/claude-4.5-sonnet
and more

Endpoint

POST https://go.fastrouter.ai/api/v1/chat/completions

Base URL

https://go.fastrouter.ai/api/v1

Payload fields include:

model: Model ID (provider/model)
messages: Array of chat messages
stream (optional): Enables streaming responses

Using the OpenAI SDK

FastRouter is fully compatible with the OpenAI SDK. Just point the SDK to FastRouter’s base URL.

from openai import OpenAI

client = OpenAI(
    base_url="https://go.fastrouter.ai/api/v1",  # FastRouter base URL
    api_key="<FASTROUTER_API_KEY>",  # Replace with your FastRouter API key
)

completion = client.chat.completions.create(
    model="anthropic/claude-4.5-sonnet",  # Replace with your model ID
    messages=[
        {"role": "user", "content": "What is the meaning of life?"}
    ]
)

print(completion.choices[0].message.content)

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: 'https://go.fastrouter.ai/api/v1', // FastRouter base URL
  apiKey: '<FASTROUTER_API_KEY>', // Replace with your FastRouter API key
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: 'anthropic/claude-4.5-sonnet', // Replace with your model ID
    messages: [
      { role: 'user', content: 'What is the meaning of life?' }
    ]
  });
  
  console.log(completion.choices[0].message);
}

main();

Calling FastRouter Directly (No SDK)

Perfect for scripts, testing, or minimal environments.

curl --location 'https://go.fastrouter.ai/api/v1/chat/completions' \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <FASTROUTER_API_KEY>' \
  --data '{
    "model": "google/gemini-3-pro-preview",
    "messages": [
      { "role": "user", "content": "hello world" }
    ],
    "stream": true
  }'

const API_URL = 'https://go.fastrouter.ai/api/v1/chat/completions'; // FastRouter API endpoint

const response = await fetch(API_URL, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer <FASTROUTER_API_KEY>', // Replace <FASTROUTER_API_KEY> with your actual API key
  },
  body: JSON.stringify({
    model: 'anthropic/claude-4.5-sonnet', // Replace with your model ID
    messages: [
      { role: 'user', content: 'hello world' }
    ],
    stream: true
  })
});

const data = await response.json();
console.log(data);

url = "https://go.fastrouter.ai/api/v1/chat/completions"  # FastRouter API endpoint

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer <FASTROUTER_API_KEY>"  # Replace <FASTROUTER_API_KEY> with your actual API key
}

data = {
    "model": "anthropic/claude-4.5-sonnet",  # Replace with your model ID
    "messages": [
        {"role": "user", "content": "hello world"}
    ],
    "stream": True
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

String url = "https://go.fastrouter.ai/api/v1/chat/completions"; // FastRouter API endpoint

String requestBody = """
    {
        "model": "anthropic/claude-4.5-sonnet",
        "messages": [
            { "role": "user", "content": "hello world" }
        ],
        "stream": true
    }
    """;

HttpClient client = HttpClient.newHttpClient();

HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create(url))
    .header("Content-Type", "application/json")
    .header("Authorization", "Bearer <FASTROUTER_API_KEY>") // Replace with your actual API key
    .POST(HttpRequest.BodyPublishers.ofString(requestBody))
    .build();

HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());

System.out.println(response.body());

<?php

$url = "https://go.fastrouter.ai/api/v1/chat/completions"; // FastRouter API endpoint

$data = [
    "model" => "anthropic/claude-4.5-sonnet", // Replace with your model ID
    "messages" => [
        [
            "role" => "user",
            "content" => "hello world"
        ]
    ],
    "stream" => true
];

$options = [
    "http" => [
        "header" => [
            "Content-Type: application/json",
            "Authorization: Bearer <FASTROUTER_API_KEY>" // Replace <FASTROUTER_API_KEY> with your actual API key
        ],
        "method" => "POST",
        "content" => json_encode($data)
    ]
];

$context = stream_context_create($options);
$response = file_get_contents($url, false, $context);

echo $response;

?>

Key Takeaway

FastRouter’s Chat Completion endpoint makes AI integration simple by:

Mimicking OpenAI’s schema
Supporting SDKs across languages
Allowing direct HTTP calls
Supporting streaming
Letting you route requests to the best models from multiple providers

PreviousWeb Search NextResponses API

Last updated 1 month ago