Skip to content

Create Response API - POST /v1/responses

Endpoint

POST https://api.tokenrouter.io/v1/responses

Request

const response = await client.responses.create({
  model: 'auto:balance',
  input: 'Hello!',
  temperature: 0.7,
  max_output_tokens: 1000
});

response = client.responses.create(
    model="auto:balance",
    input="Hello!",
    temperature=0.7,
    max_output_tokens=1000
)

curl https://api.tokenrouter.io/v1/responses \
  -H "Authorization: Bearer tr_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto:balance",
    "input": "Hello!",
    "temperature": 0.7,
    "max_output_tokens": 1000
  }'

Parameters

Parameter	Type	Required	Description
`model`	string	No	Routing mode or model (default: `auto:balance`)
`input`	string	Yes	Text input
`instructions`	string	No	System instructions
`max_output_tokens`	integer	No	Max response length
`temperature`	number	No	0-2, default 1
`stream`	boolean	No	Enable streaming

See the OpenAPI spec for all parameters.

Response

{
  "id": "resp_...",
  "object": "response",
  "created_at": 1704067200,
  "status": "completed",
  "model": "gpt-4o-2024-11-20",
  "output": [
    {
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "Hello! How can I help you?"
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 5,
    "output_tokens": 8,
    "total_tokens": 13
  },
  "metadata": {
    "provider": "openai",
    "routing_mode": "balance"
  }
}

Next Steps