Quick Start

RouteAPI gives your application one authenticated entry point for OpenAI-compatible, Claude Messages, and Google Gemini APIs. This guide takes you from an account to a verified request, then points you to the right integration path for production.

What you need before starting

A RouteAPI account, a token created in the console, and a model ID that is available to that token. Keep the token on a server or in an environment variable; never commit it to a repository or expose it in browser code.

Get access in three steps

1. Register an account. Visit the RouteAPI Console and register with email or Google. The dashboard shows your balance, usage, and account status.
2. Create a token. Open Token Management → Create Key. Give the token a recognizable name, set an expiration date, and optionally add quota and model limits.
3. Send a test request. Set ROUTEAPI_KEY to the new token, choose an available model, and run the cURL example below.

Use the model ID, not its display name

Model availability and capabilities are token-specific. Check the model list before your first call and use the returned id value in the request.

Send a request

The OpenAI-compatible endpoint is the shortest path for a first test. It accepts the same basic chat format used by many existing clients.

export ROUTEAPI_KEY="sk-your-routeapi-token"

curl https://api.routeapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $ROUTEAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      {"role": "user", "content": "Hello RouteAPI"}
    ]
  }'

The response contains the assistant message and usage information. Keep the request ID returned by the API or client when available; it is useful for troubleshooting. If the model name is not available for your token, replace it with an ID returned by GET /v1/models.

Choose an integration path

Direct API Use cURL or any HTTP client when you need full control and no extra dependency.

OpenAI-compatible SDK Keep your existing OpenAI SDK code and change only the API key and Base URL.

Developer clients Configure Codex, Cursor, Claude Code, OpenCode, LangChain, or LiteLLM with RouteAPI.

Node.js and Python

RouteAPI is compatible with the official OpenAI SDKs. Choose your runtime, install its SDK, then set the RouteAPI Base URL:

# Node.js
bun add openai

# Python
pip install openai

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.ROUTEAPI_KEY,
  baseURL: 'https://api.routeapi.ai/v1',
});

const response = await client.chat.completions.create({
  model: 'gpt-5.5',
  messages: [{ role: 'user', content: 'Introduce RouteAPI in one sentence' }],
});

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

See the complete Node.js, Python, and OpenAI SDK examples.

Stream incremental output

Set stream to true to receive Server-Sent Events (SSE) as the model produces output. Read each data: event and stop when you receive data: [DONE].

curl https://api.routeapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $ROUTEAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "stream": true,
    "messages": [
      {"role": "user", "content": "Explain RouteAPI in three points"}
    ]
  }'

Streaming support and final usage events depend on the selected model. See Streaming Responses for SSE handling and mid-stream errors.

Verify and troubleshoot

Before integrating a larger application, use the same token to verify the model list and a real request:

curl https://api.routeapi.ai/v1/models \
  -H "Authorization: Bearer $ROUTEAPI_KEY"

• 401 — verify the token and the Authorization header.
• 402 — check the account balance or token quota.
• 429 — reduce request frequency and review rate limits.
• 502/503 — check model service availability, try a supported model, or retry with a limit.
• Model unavailable — confirm the exact model ID and its capabilities.

Use Request Debugging and Common Errors for a deeper diagnosis. The console usage log includes status, latency, tokens, cost, and error details.

Continue with RouteAPI

API Overview Compare protocol entry points, Base URLs, headers, and capability limits.

Models and pricing Inspect model IDs, capabilities, availability, and current rates.

Routing and fallback Understand service paths, model mapping, and failure protection before production.

For production, keep tokens server-side, pin model IDs, record request IDs, and test optional features such as streaming, tool calling, structured outputs, and multimodal input with the exact model you plan to use.