Skip to main content

​
AI API

Endpoints for interacting with AI models through a unified provider layer. These endpoints are served by the backend API and do not require session authentication.

​
List models (frontend)

GET /api/models
Returns available AI models from OpenRouter with additional featured models. No authentication required.

​
Response

{
  "models": [
    {
      "id": "anthropic/claude-sonnet-4-20250514",
      "name": "Claude Sonnet",
      "contextLength": 200000,
      "pricing": {
        "prompt": 0.003,
        "completion": 0.015
      },
      "featured": true,
      "description": "Anthropic's Claude Sonnet model"
    }
  ]
}

​
Errors

CodeDescription
500Failed to fetch models or invalid response from provider

​
Health check

GET /api/ai/health
Returns the availability status of configured AI providers.

​
Response

{
  "status": "healthy",
  "providers": {
    "openrouter": true
  },
  "timestamp": "2026-03-19T00:00:00Z"
}
The status field is healthy when all providers are reachable and degraded when one or more are down.

​
Errors

CodeDescription
503AI service unavailable

​
List models

GET /api/ai/models
Returns all available AI models across providers.

​
Response

{
  "models": [
    {
      "id": "anthropic/claude-sonnet-4-20250514",
      "provider": "openrouter"
    }
  ],
  "count": 1,
  "openrouter": 1,
  "timestamp": "2026-03-19T00:00:00Z"
}

​
List models by provider

GET /api/ai/models/:provider

​
Path parameters

ParameterTypeDescription
providerstringProvider name (for example, openrouter)

​
Response

{
  "provider": "openrouter",
  "models": [],
  "count": 0,
  "timestamp": "2026-03-19T00:00:00Z"
}

​
Select model

POST /api/ai/models/select
Automatically selects the best model for a given task type.

​
Request body

FieldTypeRequiredDescription
taskTypestringNoType of task (default: general)

​
Response

{
  "model": {
    "id": "anthropic/claude-sonnet-4-20250514",
    "provider": "openrouter"
  },
  "taskType": "general",
  "timestamp": "2026-03-19T00:00:00Z"
}

​
Errors

CodeDescription
404No models available

​
Chat completion

POST /api/ai/chat
Send a chat completion request through the unified AI provider layer. The model is auto-selected if not specified.

​
Request body

FieldTypeRequiredDescription
messagesarrayYesArray of message objects with role (user, assistant, or system) and content
modelstringNoModel ID. Auto-selected based on taskType if omitted.
taskTypestringNoUsed for auto-selection when model is omitted
temperaturenumberNoSampling temperature
top_pnumberNoNucleus sampling parameter
max_tokensnumberNoMaximum tokens in the response

​
Example request

{
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Hello!" }
  ],
  "temperature": 0.7,
  "max_tokens": 1024
}

​
Response

Returns the AI provider’s chat completion response. The exact shape depends on the provider used.

​
Errors

CodeDescription
400Messages array is required and must be non-empty
404No models available
500AI provider error

​
Estimate cost

POST /api/ai/estimate-cost
Estimate the cost of a request based on token counts and model pricing.

​
Request body

FieldTypeRequiredDescription
modelstringYesModel ID
inputTokensnumberYesNumber of input tokens
outputTokensnumberYesNumber of output tokens

​
Response

{
  "model": "anthropic/claude-sonnet-4-20250514",
  "inputTokens": 1000,
  "outputTokens": 500,
  "estimatedCost": 0.0045,
  "currency": "USD",
  "timestamp": "2026-03-19T00:00:00Z"
}

​
Errors

CodeDescription
400Model, inputTokens, and outputTokens are all required