AI API

Endpoints

Method	Path	Purpose
POST	/v1/{app_id}/chat/completions	Chat completion (OpenAI-compatible)
POST	/v1/{app_id}/embeddings	Generate embeddings
GET	/v1/{app_id}/ai/config	Get AI configuration
PUT	/v1/{app_id}/ai/config	Update AI configuration
GET	/v1/{app_id}/ai/usage	Get AI usage statistics

Chat completions

POST /v1/{app_id}/chat/completions
Authorization: Bearer {token}

{
  "model": "anthropic/claude-3.5-sonnet",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Hello!" }
  ],
  "max_tokens": 500,
  "temperature": 0.7,
  "stream": false
}

Standard OpenAI-compatible response format. Set "stream": true for server-sent events.

Embeddings

POST /v1/{app_id}/embeddings
Authorization: Bearer {token}

{
  "model": "openai/text-embedding-3-small",
  "input": "What is Butterbase?",
  "encoding_format": "float"
}

Parameter	Description
model	Embedding model ID (required)
input	String or array of strings (required)
encoding_format	"float" (default) or "base64"

Available embedding models

Model	ID	Dimensions
Text Embedding 3 Small	openai/text-embedding-3-small	1536
Text Embedding 3 Large	openai/text-embedding-3-large	3072
Text Embedding Ada 002	openai/text-embedding-ada-002	1536

Configuration

PUT /v1/{app_id}/ai/config

{
  "defaultModel": "anthropic/claude-3.5-sonnet",
  "byokKey": "sk-or-...",
  "maxTokensPerRequest": 4096,
  "allowedModels": ["anthropic/claude-3.5-sonnet"]
}

Field	Description
defaultModel	Model used when none specified
byokKey	Your OpenRouter API key (encrypted)
maxTokensPerRequest	Token limit per request (1-100,000)
allowedModels	Restrict allowed models

Usage

GET /v1/{app_id}/ai/usage?startDate=2026-01-01&endDate=2026-01-31

Response:

{
  "totalTokens": 150000,
  "totalCost": 0.45,
  "byModel": {
    "anthropic/claude-3.5-sonnet": {
      "tokens": 120000,
      "cost": 0.40,
      "requests": 25
    }
  }
}