Text Generation

POST /v1/responses

OpenAI Responses-style text generation endpoint.

Generate text with an OpenAI Responses-compatible request and response format.

Description

This endpoint is designed for OpenAI Responses-style integrations. It supports standard JSON responses as well as streaming, and is a good fit for new text generation applications that want a modern OpenAI-compatible interaction model.

Headers

Name	Type	Required	Description
`Authorization`	string	Yes	Bearer token in the format `Bearer YOUR_API_KEY`.
`Content-Type`	string	Yes	Must be `application/json`.

Request body parameters

Name	Type	Required	Description
`model`	string	Yes	Model ID to use for generation.
`input`	string / array	Yes	Input content for the model.
`instructions`	string	No	High-level instruction applied to the request.
`stream`	boolean	No	Whether to return SSE streaming events.
`temperature`	number	No	Sampling temperature.
`top_p`	number	No	Nucleus sampling parameter.
`max_output_tokens`	integer	No	Maximum output token count.
`tools`	array	No	Tool definitions available during generation.
`tool_choice`	string / object	No	Tool calling strategy.
`metadata`	object	No	Optional metadata for your own tracking.

Supported models

Model
`gpt-5.4`
`gpt-5.4-mini`
`gpt-5.4-nano`
`gpt-5.2`
`gpt-5`
`gpt-5-mini`
`gpt-5-nano`
`gpt-4.1`
`gpt-4.1-mini`
`gpt-4o`
`gpt-4o-mini`

Example request

cURL

curl https://api.apifree.ai/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1-mini",
    "input": "Write three taglines for a multimodal AI API platform.",
    "stream": false
  }'

Response schema

A successful response typically includes:

Field	Type	Description
`id`	string	Unique response ID.
`object`	string	Object type, such as `response`.
`created_at`	integer	Unix timestamp for creation time.
`status`	string	Current response status.
`model`	string	Model used for generation.
`output`	array	Generated content output.
`usage`	object	Token usage information.

Example response:

{
  "id": "resp_123",
  "object": "response",
  "created_at": 1750000000,
  "status": "completed",
  "model": "gpt-4.1-mini",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "One API for every model."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 12,
    "output_tokens": 18,
    "total_tokens": 30
  }
}

Streaming

If stream is true, the endpoint returns OpenAI-style SSE events. Consume the stream until the terminal completion event is received.

Errors

Errors are returned as JSON error objects. Typical cases include:

Missing or invalid model
Invalid JSON request body
Authentication failure
Upstream request failure