Responses

The Responses API uses input as a unified input field. It is designed for newer OpenAI Responses-style models and supports streaming, tools, reasoning options and response continuation.

Endpoints

Method	Path	Description
`POST`	`/v1/responses`	Create a response
`POST`	`/v1/responses/compact`	Responses compaction API with fewer fields

Request Fields

Field	Type	Required	Description
`model`	string	Yes	Model ID
`input`	string or array	Yes	Input content. Can include `input_text`, `input_image` and `input_file`
`instructions`	string	No	System-level instructions
`stream`	boolean	No	Return an SSE stream
`max_output_tokens`	integer	No	Maximum output tokens
`temperature`, `top_p`	number	No	Sampling controls
`tools`, `tool_choice`	array/object	No	Tool configuration
`parallel_tool_calls`	boolean	No	Allow parallel tool calls
`max_tool_calls`	integer	No	Maximum tool calls
`previous_response_id`	string	No	Continue from a previous response
`reasoning`	object	No	Reasoning options such as `effort` and `summary`
`text`	object	No	Text output configuration
`include`, `truncation`	any	No	OpenAI Responses extension fields
`metadata`, `user`	any	No	Metadata or user identifier
`store`, `service_tier`, `safety_identifier`	any	No	OpenAI extension fields; channel settings may filter them

curl

curl https://api.tensoraxis.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TENSORAXIS_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "input": "Explain what an API gateway is in two sentences"
  }'

Multimodal Input

{
  "model": "gpt-4o",
  "input": [
    {
      "role": "user",
      "content": [
        {"type": "input_text", "text": "Describe this image"},
        {"type": "input_image", "image_url": "https://example.com/image.png"}
      ]
    }
  ]
}

Compaction API

/v1/responses/compact accepts a smaller request body:

Field	Type	Required	Description
`model`	string	Yes	Model ID
`input`	any	No	Input to compact
`instructions`	any	No	Instructions
`previous_response_id`	string	No	Previous response ID

Response Shape

Responses follow the OpenAI Responses-style shape. Core fields include id, model, output and usage. Streaming responses return incremental content as SSE events.