API Reference

Complete reference for the LLMAI API — endpoint, authentication, request format, and response structure.

Endpoint

Every request goes to:

https://api.llmai.dev/v1

LLMAI implements the OpenAI Chat Completions interface, so any library or tooling built for that format works out of the box — just swap the base URL and API key.

Authentication

Attach your LLMAI key to every request using the Authorization header:

Authorization: Bearer YOUR_API_KEY

Keys are generated in the developer console. A missing or expired key returns 401 Unauthorized.

Compatibility Summary

Parameter	Value
Base URL	`https://api.llmai.dev/v1`
Key format	`sk-llmaai-...`
Chat endpoint	`/v1/chat/completions`
Model list endpoint	`/v1/models`
Wire protocol	OpenAI Chat Completions

Sending a Chat Request

Required Fields

{
  "model": "gpt-5.4",
  "messages": [
    { "role": "system", "content": "You are a precise technical writer." },
    { "role": "user",   "content": "Describe API rate limits in two sentences." }
  ]
}

Field	Type	Description
`model`	string	Exact model slug — see the Models page
`messages`	array	List of message objects, each with `role` and `content`

Optional Fields

Field	Type	Default	Notes
`temperature`	float	`1.0`	Controls output randomness; valid range 0–2
`max_tokens`	int	model max	Hard cap on tokens generated in this response
`stream`	bool	`false`	Set `true` to receive incremental SSE chunks
`top_p`	float	`1.0`	Nucleus sampling — alternative to `temperature`

Response Structure

{
  "id": "chatcmpl-xyz789",
  "object": "chat.completion",
  "created": 1714000000,
  "model": "gpt-5.4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Rate limits cap the number of requests per unit time..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 30,
    "completion_tokens": 18,
    "total_tokens": 48
  }
}

The usage block reflects the exact token counts billed for this call.

Streaming

Pass "stream": true to receive a stream of server-sent events (SSE). The connection stays open and each chunk arrives as a data: line:

curl https://api.llmai.dev/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-flash-preview",
    "messages": [{"role": "user", "content": "List five programming languages."}],
    "stream": true
  }'

The stream terminates with a final data: [DONE] line. Handle it in your client to know when the response is complete.

Error Reference

Status	Meaning	Action
`400`	Malformed request body	Check JSON syntax and required fields
`401`	Invalid or missing API key	Verify the `Authorization` header
`402`	Insufficient balance	Add credit at console.llmai.dev/billing
`404`	Unknown model slug	Cross-check slug spelling in the Models reference
`429`	Request rate exceeded	Reduce request frequency or add retry backoff
`500`	Upstream error	Retry; open a support ticket if it persists

On this page