GPT-4.1 Nano

POST/v1/responses

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.

Request body

Parameters supported by the OpenAI Responses API. Values, defaults, and limits are read from the model registry.

string | array<object>inputrequired

Input text or structured content for the response.

Optional<integer>max_tokens

Maximum number of tokens the model may generate in the response.

Maximum: 32768

Optional<number>temperature

Sampling temperature. Lower values are more deterministic; higher values are more creative.

Range: 0 to 2

Default: 1

Optional<number>top_p

Nucleus sampling threshold. Use this or temperature, but usually not both.

Range: 0 to 1

Optional<boolean>stream

When true, returns incremental Server-Sent Events instead of one completed response.

Default: false

Optional<array>tools

Tool definitions that the model may call during the response.

Optional<string>tool_choice

Controls whether the model may call a tool and, when supported, which tool it must call.

Optional<object>response_format

Controls the response format, including JSON mode or structured JSON output when supported.

Optional<integer>seed

Seed used to make sampling more reproducible when the provider supports it.

Response Schema

Fields returned by the OpenAI Responses API.

stringidrequired

Unique response identifier.

stringobjectrequired

Response object type.

stringstatusrequired

Response lifecycle status.

stringmodelrequired

Model that generated the response.

array<object>outputrequired

Generated response output items.

Optional<object>usage

Token usage when available.

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: chat, vision, structured_output, function_calling

integercontext_lengthrequired

Maximum context window accepted by this model.

Default: 1047576 tokens

stringexecution_moderequired

Execution mode declared by the model registry.

Default: sync

curl -X POST https://api.agrouter.ai/v1/responses \
  -H "Authorization: Bearer $AGROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-4.1-nano",
  "input": "Describe this product in one sentence."
}'

Response200 OK

{
  "id": "resp_abc123",
  "object": "response",
  "status": "completed",
  "model": "gpt-4.1-nano",
  "output": [
    {
      "type": "message",
      "content": [
        {
          "type": "output_text",
          "text": "A concise product description."
        }
      ]
    }
  ]
}