Responses — DataMind AI Docs

API Reference/Responses (recommended)

Endpoint#

Endpoint

POST https://xpluse.plus/v1/responses

Create model responses with text and image input, producing text or JSON output. Supports function calling, streaming responses, and multi-turn conversations. DataMind AI recommends this API for new projects because it offers native Prompt Caching, structured item mode, and richer streaming events.

Request parameters#

Parameter	Type	Required	Description
`Models`	string	✅	Model identifier
`input`	string \| array	✅	Input content, either plain text or a structured message array
`instructions`	string	—	System instructions, independently eligible for Prompt Caching
`stream`	boolean	—	Whether to enable SSE streaming; default `false`
`max_output_tokens`	number	—	Maximum generated token count
`temperature`	number	—	Sampling temperature from 0 to 2; default is 1
`tools`	array	—	Available tool definitions
`tool_choice`	string \| object	—	`auto`、`none` or a specified tool
`store`	boolean	—	Whether to store the response; default `true`
`provider`	object	—	DataMind AI routing and fallback extension

Request example#

cURL

curl https://xpluse.plus/v1/responses \
  -H "Authorization: Bearer $DATAMIND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "input": "Explain what an API Gateway is",
    "instructions": "You are a helpful technical assistant. Answer in English.",
    "max_output_tokens": 1024
  }'

Python

from openai import OpenAI

client = OpenAI(base_url="https://xpluse.plus/v1", api_key="<your DATAMIND_API_KEY>")

response = client.responses.create(
    model="openai/gpt-5.4-mini",
    input="Explain what an API Gateway is",
    instructions="You are a helpful technical assistant. Answer in English.",
    max_output_tokens=1024
)

print(response.output_text)

TypeScript

const response = await client.responses.create({
  model: 'openai/gpt-5.4-mini',
  input: 'Explain what an API Gateway is',
  instructions: 'You are a helpful technical assistant. Answer in English.',
  max_output_tokens: 1024
})

console.log(response.output_text)

ResponseFormat#

JSON

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1703123456,
  "model": "openai/gpt-5.4-mini",
  "status": "completed",
  "output": [
    {
      "type": "message",
      "id": "msg_def456",
      "status": "completed",
      "role": "assistant",
      "content": [{"type": "output_text", "text": "An API Gateway is a...", "annotations": []}]
    }
  ],
  "usage": {"input_tokens": 25, "output_tokens": 150, "total_tokens": 175}
}

Streaming event types#

Event type	Description
`response.created`	Response object created
`response.output_text.delta`	Text delta
`response.output_item.done`	Output item completed
`response.completed`	Response completed
`response.function_call_arguments.delta`	Function call argument delta

Last updated on June 22, 2026