Quickstart

Sign in, create an API key, top up some balance, and call any OpenAI-compatible client against https://api.tokenroute.io/v1.

curl https://api.tokenroute.io/v1/chat/completions \
  -H "Authorization: Bearer $TOKENROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5",
    "messages": [{"role": "user", "content": "Write a haiku about routing."}]
  }'

Authentication

Pass your key as a Bearer token. Keys start with sk-tr-. The platform secret is shown once at creation — store it as an env var; we don't keep a copy you can read.

Authorization: Bearer sk-tr-XXXXXXXXXXXXXXXXXXXXXXXX

Models

Pass any of these strings as the model field. Each forwards to the corresponding upstream — your tokenroute key is the only credential you carry.

Examples

Python (openai SDK)

from openai import OpenAI

client = OpenAI(
    api_key="sk-tr-...",
    base_url="https://api.tokenroute.io/v1",
)

resp = client.chat.completions.create(
    model="claude-sonnet-4-5",  # or gpt-4o, gemini-2.5-pro, deepseek-reasoner…
    messages=[{"role": "user", "content": "Prove there are infinitely many primes."}],
)
print(resp.choices[0].message.content)

Node (openai SDK)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.TOKENROUTE_API_KEY,
  baseURL: 'https://api.tokenroute.io/v1',
});

const resp = await client.chat.completions.create({
  model: 'gpt-4o-mini',  // or claude-sonnet-4-5, gemini-2.5-pro, etc.
  messages: [{ role: 'user', content: 'Hello' }],
});
console.log(resp.choices[0].message.content);

Streaming

curl https://api.tokenroute.io/v1/chat/completions \
  -H "Authorization: Bearer $TOKENROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5",
    "stream": true,
    "messages": [{"role": "user", "content": "Count to 5."}]
  }'

Error codes

Rate limits

Each key can carry an RPM (requests/min) and TPM (tokens/min) cap. Defaults: unlimited. When you hit the wall, you get HTTP 429 with Retry-After in seconds and an error payload like:

{
  "error": {
    "message": "Rate limit exceeded (rpm). Retry after 12s.",
    "type": "rate_limit_error",
    "code": 429
  }
}

OpenAI compatibility

We implement the chat-completions surface POST /v1/chat/completions and GET /v1/models. Streaming, function calling, multi-turn, system prompts — pass them through as-is. Embeddings and Assistants are not supported yet.