Create a Response¶

Submit input to generate a Response and read generated text from its output items.

POST https://token.moi.matrixorigin.cn/v1/responses

Before you begin¶

Prepare a personal access token or service account API key for Genesis. See Access credentials for credential selection and permissions.
Use List callable models to select a model that supports Responses.

Request body¶

Replace $GENESIS_ACCESS_TOKEN and $MODEL_ID with your credential and the selected model ID.

Request example

curl -X POST \
  "https://token.moi.matrixorigin.cn/v1/responses" \
  -H "Authorization: Bearer $GENESIS_ACCESS_TOKEN" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "'"$MODEL_ID"'",
  "input": "Reply with OK.",
  "store": false,
  "max_output_tokens": 256
}'

Parameters

The fields below cover text generation. Tools, multimodal input, and state references require corresponding model capabilities and request configuration.

Parameter	Type	Required	Description
`model`	string	Yes	Selected model ID from `data[].id` in the model list.
`input`	string or array of object	Yes	Text input or ordered text messages.
`input[].role`	string	Required for a message array	Message role; the example uses `user`.
`input[].content`	string or array of object	Required for a message array	Message text or input text blocks.
`input[].content[].type`	string	Required for a text block	Use `input_text` for an input text block.
`input[].content[].text`	string	Required for a text block	Input text.
`store`	boolean	No	Whether to store the Response. The example disables storage. With a personal access token and model-service storage support, set to `true` to retrieve or delete it later.
`max_output_tokens`	integer	No	Output token limit; reasoning models can include reasoning tokens in this budget.
`instructions`	string	No	Additional instructions for this generation.
`temperature`	number	No	Sampling temperature, when supported by the selected model.
`top_p`	number	No	Nucleus sampling parameter, when supported by the selected model.
`stream`	boolean	No	Set to `true` for Responses SSE events; streaming cannot be enabled together with storage.

Successful response¶

A successful request returns the generated output and its status. Check the status to determine whether the output is complete.

Response example

{
  "id": "resp-example",
  "object": "response",
  "status": "completed",
  "model": "MODEL_ID",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "OK"
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 12,
    "output_tokens": 1,
    "total_tokens": 13
  }
}

Fields

Field	Type	Description
`id`	string	Response identifier; use it to retrieve or delete a stored response.
`object`	string	Object type `response`.
`status`	string	Generation status, such as `completed`; check it to determine whether output is complete.
`model`	string	Model that processed the request.
`output`	array of object	Output items; text messages may follow reasoning items.
`output[].type`	string	Output type, such as `message` or `reasoning`.
`output[].role`	string	Role of a message output item.
`output[].content`	array of object	Content blocks in a message output item.
`output[].content[].type`	string	Generated text blocks use `output_text`.
`output[].content[].text`	string	Generated text.
`output[].summary`	array of object	Summary returned with a reasoning item, when present.
`output[].summary[].type`	string	Summary block type, such as `summary_text`.
`output[].summary[].text`	string	Summary text.
`usage`	object	Token usage for this request.
`usage.input_tokens`	integer	Input tokens.
`usage.output_tokens`	integer	Output tokens.
`usage.total_tokens`	integer	Total tokens.

Error response¶

A missing model ID returns HTTP 400. Supply the model ID before sending the request again.

Response example

{
  "error": {
    "message": "missing required parameter: model",
    "type": "invalid_request",
    "code": "invalid_request"
  }
}

Fields

Field	Type	Description
`error`	object	Error details.
`error.message`	string	Error description; the example indicates a missing model ID.
`error.type`	string	Error type; may be omitted by a model service.
`error.code`	string or null	Error code; may be omitted by a model service.

Next steps¶

For a response created with a personal access token and storage enabled, use its id to Retrieve a Response. Delete the Response when no longer needed. Full-content retrieval and retention depend on the selected model service.

Last updated on Oct 19, 2026