API Reference

Send a list of messages and receive a complete response. Requires a valid API key.

Request body

Example

Copy

Copy

Copy

Response

{
  "id": "nexa-a1b2c3d4e5f6",
  "object": "nexa.chat.completion",
  "created": 1789500000,
  "model": "nexaai-0.1",
  "output": "Hello! How can I help you today?",
  "finish_reason": "stop"
}

Same request body as chat completions, returns a server-sent event stream instead of waiting for the full response.

Response (text/event-stream)

data: {"token": "Hello"}

data: {"token": "!"}

data: {"done": true}

List models currently available on this NexaAI deployment. No authentication required.

Response

{
  "object": "list",
  "data": [
    { "id": "nexaai-0.1", "status": "active" }
  ]
}

Real-time status of the API and inference backend. No authentication required.

Response

{
  "api": "operational",
  "inference": "operational",
  "checked_at": 1789500000
}

inference is one of operational, degraded, or unavailable — checked live against the inference backend on every call, not a static value.

Public, platform-wide activity counters. No authentication required, no per-user data returned.

Response

{
  "total_requests": 142,
  "total_accounts": 9
}

Both counts are read directly from stored request logs and accounts — not estimated or rounded.

Create a new API key. Requires an active dashboard session (not an API key — this is a session-authenticated account management endpoint).

Request body

Response

{
  "api_key": "nexa_live_...",
  "key_id": 1,
  "prefix": "nexa_live_a8f3k2m1",
  "label": "Production",
  "daily_limit": 200,
  "warning": "Save this key now. It cannot be shown again."
}