Endpoints

Base URL: https://api.mantler.ai

All endpoints that accept a body expect Content-Type: application/json.

---

GET /health

Gateway health check. No authentication required.

Response:

{ "status": "ok" }

---

GET /v1/models

List the models available to your API key.

Request:

GET /v1/models
Authorization: Bearer mk_live_YOUR_KEY

Response:

{
  "object": "list",
  "data": [
    {
      "id": "llama3.1:8b",
      "object": "model",
      "created": 1713000000,
      "owned_by": "mantler"
    }
  ]
}

Each id is the model identifier to use in chat completions requests. Model IDs correspond to the model layer of a deployed mantle.

---

POST /v1/chat/completions

Generate a chat completion. Follows the OpenAI chat completions spec.

Request:

POST /v1/chat/completions
Authorization: Bearer mk_live_YOUR_KEY
Content-Type: application/json

{
  "model": "llama3.1:8b",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "What is the capital of France?" }
  ],
  "stream": false,
  "temperature": 0.7,
  "max_tokens": 512
}

Parameter	Type	Required	Description
model	string	Yes	Model ID from /v1/models
messages	array	Yes	Conversation history
stream	boolean	No	Stream tokens as SSE. Default false.
temperature	number	No	Sampling temperature (0–2). Default 1.
max_tokens	integer	No	Max tokens to generate.
top_p	number	No	Nucleus sampling. Default 1.
stop	string|array	No	Stop sequences.

Non-streaming response:

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1713000000,
  "model": "llama3.1:8b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 9,
    "total_tokens": 33
  }
}

Streaming response ("stream": true):

Returns server-sent events (SSE). Each event is a data: line containing a partial completion object. The stream ends with data: [DONE].

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"delta":{"role":"assistant","content":"The"},"index":0}]}

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"delta":{"content":" capital"},"index":0}]}

data: [DONE]

---

Error responses

The API returns standard HTTP status codes with a JSON error body:

{
  "error": {
    "message": "Invalid API key",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}

Status	Meaning
401	Invalid or missing API key
403	Key does not have access to the requested model
404	Model not found or not deployed
429	Rate limit exceeded
503	Machine offline or runtime unavailable