Quick Start
5 min setupGet up and running with TokenRouter in minutes. This guide will walk you through making your first API call.
Prerequisites
- A TokenRouter account (sign up at tokenrouter.com)
- At least one provider API key (OpenAI, Anthropic, Mistral, or Together.ai)
- Basic knowledge of REST APIs
Step 1: Get Your API Key
First, you'll need to generate a TokenRouter API key from your dashboard.
1. Log in to your TokenRouter dashboard
2. Navigate to API Keys section
3. Click "Generate New Key"
4. Copy your API key (starts with `tr_`)
Important: Keep your API key secure and never expose it in client-side code. Store it as an environment variable.
Step 2: Configure Provider Keys
Add your provider API keys to enable intelligent routing across different models.
OpenAI
GPT-4, GPT-3.5 Turbo models
sk-...Anthropic
Claude 3 Opus, Sonnet, Haiku
sk-ant-...Mistral AI
Mistral Large, Medium, Small
...Together.ai
Llama 2, Code Llama, others
...Step 3: Make Your First Request
Now you're ready to make your first API call. Choose your preferred method below:
curl -X POST https://api.tokenrouter.com/route \
-H "Authorization: Bearer tr_your_api_key_here" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Explain quantum computing in simple terms",
"temperature": 0.7,
"max_tokens": 1000
}'Expected Response
You'll receive a response in OpenAI-compatible format with additional TokenRouter metadata:
{
"id": "tr_req_abc123",
"object": "chat.completion",
"created": 1699564800,
"model": "gpt-4",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Quantum computing is like having a super-powered calculator..."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 12,
"completion_tokens": 150,
"total_tokens": 162
},
"tokenrouter": {
"selected_provider": "openai",
"selected_model": "gpt-4",
"routing_reason": "optimal_quality_cost_ratio",
"cost_savings": "23%",
"response_time_ms": 1250
}
}