API Overview — DataMind AI Docs

DataMind AI provides API access through three protocols, each compatible with the corresponding official provider SDK.

Base URLs#

Protocol	Base URL	Description
OpenAI-compatible	`https://xpluse.plus/v1`	Compatible with the OpenAI SDK; supports Chat Completions and the Responses API
Anthropic native	`https://api.xpluse.plus/anthropic`	Compatible with the Anthropic SDK
Gemini native	`https://api.xpluse.plus/gemini`	Compatible with the Google GenAI SDK

Authentication#

All three protocols use the same DataMind AI Key, but the header format differs:

Protocol	Header	Format
OpenAI	`Authorization`	`Bearer sk-xxx`
Anthropic	`x-api-key`	`sk-xxx`
Gemini	`x-goog-api-key`	`sk-xxx`

Available endpoints#

OpenAI-compatible

/v1/chat/completions（POST）—— Chat completions
/v1/responses（POST）—— Responses API (recommended)
/v1/embeddings（POST）—— Embeddings
/v1/images/generations（POST）—— Image generation
/v1/models（GET）—— Model list
/v1/models/count（GET）—— Model count

Anthropic native

/anthropic/v1/messages（POST）—— Create messages (recommended)
/anthropic/v1/models（GET）—— Model list
/anthropic/v1/models/count（GET）—— Model count

Gemini native

/gemini/v1beta/models/{model}:generateContent（POST）—— Generate content
/gemini/v1beta/cachedContents（POST）—— Explicit cache
/gemini/v1beta/models（GET）—— Model list
/gemini/v1beta/models/count（GET）—— Model count

DataMind AI OpenAPI

/v1/user/balance（GET）—— Balance query, compatible with cc-switch

Rate limits#

Pay as you go. The unified policy is 100 RPM aggregated at the team level, with no TPM limit. RPM is shared by all keys in the same team. Rate-limited requests return 429 Too Many Requests。

Error codes#

Uses standard HTTP status codes:200 success, 400 bad request, 401 authentication failed, 403 insufficient permission, 404 not found, 429 rate limited, 500 server error, 502 upstream error, 503 unavailable.

JSON

{
  "error": {
    "code": "invalid_api_key",
    "message": "The provided API Key is invalid. Check it and retry.",
    "type": "authentication_error"
  }
}

DataMind AI extension parameters#

DataMind AI provides extension parameters for advanced routing and fallback control:

JSON

{
  "model": "openai/gpt-5.4-mini",
  "messages": [...],
  "provider": {
    "routing": "cost",
    "fallback": ["anthropic/claude-sonnet-4.6", "google/gemini-3.1-flash-lite-preview"]
  }
}

Last updated on June 22, 2026