Endpoints

Base URL

Inference API requests should be sent to:


https://api.flowapi.net/v1

For platform health checks, use:


https://api.flowapi.net/healthz

Available Endpoints

Chat Completions


POST /v1/chat/completions

Create a chat completion. This is the primary endpoint for interacting with language models.

See Chat Completions for the full endpoint reference.

Headers


Authorization: Bearer YOUR_FLOW_API_KEY
Content-Type: application/json

Request Body


{
  "model": "gpt-4o",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Hello!" }
  ],
  "temperature": 0.7,
  "max_tokens": 1024,
  "stream": false
}

Response


{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1713000000,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 9,
    "total_tokens": 29
  }
}

Embeddings


POST /v1/embeddings

Generate vector embeddings for text inputs using an embedding-capable model.

See Embeddings for request and response details.

List Models


GET /v1/models

Returns a list of all models currently available through FlowAPI.

Health Check


GET /healthz

Returns the current health status of the public gateway.