Messages — DataMind AI Docs

API Reference/Messages (recommended)

Endpoint#

Endpoint

POST https://api.xpluse.plus/anthropic/v1/messages

Create Claude conversations through the Anthropic native API. DataMind AI is fully compatible with the Anthropic Messages API and works directly with the official SDK. The native protocol is better than OpenAI-compatible forwarding because it provides native Prompt Caching (up to 90% lower input cost), full feature support (Extended Thinking, Citations, PDF input), and lower latency.

Authentication#

Header

x-api-key: <your DATAMIND_API_KEY>
anthropic-version: 2023-06-01

Request parameters#

Parameter	Type	Required	Description
`Models`	string	✅	Model identifier, such as `anthropic/claude-sonnet-4.6`
`max_tokens`	number	✅	Maximum generated token count
`messages`	array	✅	Message array
`system`	string	—	System prompt
`temperature`	number	—	Sampling temperature from 0 to 1
`top_p` / `top_k`	number	—	Nucleus sampling / Top-K sampling
`stream`	boolean	—	Whether to enable streaming responses
`tools`	array	—	Tool definitions
`tool_choice`	object	—	Tool selection strategy

Request example#

cURL

curl https://api.xpluse.plus/anthropic/v1/messages \
  -H "x-api-key: $DATAMIND_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4.6",
    "max_tokens": 1024,
    "system": "You are a professional coding assistant.",
    "messages": [{"role": "user", "content": "Write a quicksort implementation in Python"}]
  }'

Python

import anthropic

client = anthropic.Anthropic(base_url="https://api.xpluse.plus/anthropic", api_key="<your DATAMIND_API_KEY>")

message = client.messages.create(
    model="anthropic/claude-sonnet-4.6",
    max_tokens=1024,
    system="You are a professional coding assistant.",
    messages=[{"role": "user", "content": "Write a quicksort implementation in Python"}]
)

print(message.content[0].text)

TypeScript

const message = await client.messages.create({
  model: 'anthropic/claude-sonnet-4.6',
  max_tokens: 1024,
  system: 'You are a professional coding assistant.',
  messages: [{ role: 'user', content: 'Write a quicksort implementation in Python' }]
})

console.log(message.content[0].text)

ResponseFormat#

JSON

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "content": [{"type": "text", "text": "Here is a Python quicksort implementation..."}],
  "model": "anthropic/claude-sonnet-4.6",
  "stop_reason": "end_turn",
  "usage": {"input_tokens": 25, "output_tokens": 200}
}

Supported models#

Model	Description
`anthropic/claude-opus-4.6`	Strongest capability
`anthropic/claude-sonnet-4.6`	Balanced performance
`anthropic/claude-haiku-4.5`	Fast response

Last updated on June 22, 2026