Skip to content

Standard Requests

Basic Request

import Tokenrouter from 'tokenrouter';

const client = new Tokenrouter({
  apiKey: process.env.TOKENROUTER_API_KEY
});

const response = await client.responses.create({
  model: 'auto:balance',
  input: 'What is the capital of France?'
});

console.log(response.output[0].content[0].text);

from tokenrouter import Tokenrouter

client = Tokenrouter(
    api_key=os.getenv("TOKENROUTER_API_KEY")
)

response = client.responses.create(
    model="auto:balance",
    input="What is the capital of France?"
)

print(response.output[0].content[0].text)

curl https://api.tokenrouter.io/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer tr_..." \
  -d '{
    "model": "auto:balance",
    "input": "What is the capital of France?"
  }'

Request Parameters

model - Routing mode or specific model (default: auto:balance)
input - Text input (required)
instructions - System instructions
max_output_tokens - Maximum response length
temperature - Randomness (0-2)
stream - Enable streaming

Response Format

{
  "id": "resp_...",
  "model": "gpt-4o-2024-11-20",
  "output": [
    {
      "role": "assistant",
      "content": [{"type": "text", "text": "Paris."}]
    }
  ],
  "usage": {
    "input_tokens": 12,
    "output_tokens": 3,
    "total_tokens": 15
  }
}

Next Steps