AI API

AI provider endpoints for model selection, chat completion, and cost estimation

AI API

Endpoints for interacting with AI models through a unified provider layer. These endpoints are served by the backend API service, not the web application. They are available at the backend base URL, which may differ from the web API base URL depending on your deployment.

These endpoints are internal backend endpoints and are not exposed through the web application’s /api routes. The health check (GET /api/ai/health) and model listing endpoints (GET /api/ai/models, GET /api/ai/models/:provider) are public and do not require authentication — they return non-sensitive data for status monitoring and pricing discovery. All other endpoints require bearer token (API key) authentication. The chat and cost estimation endpoints additionally require a valid subscription plan. All POST requests must include the Content-Type: application/json header.

All /api/ai/* endpoints share a rate limit of 30 requests per minute per IP, not just the chat endpoint.

Health check

GET /api/ai/health

No authentication required. 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.

Error response

When one or more providers fail, the response uses status: "error" and includes the error message:

{
  "status": "error",
  "error": "Provider connection failed"
}

Code	Description
503	AI service unavailable

List models

GET /api/ai/models

No authentication required. Returns all available AI models across providers. This endpoint is public to support pricing pages and model discovery.

Response

{
  "models": [
    {
      "id": "anthropic/claude-sonnet-4-20250514",
      "name": "Claude Sonnet",
      "provider": "openrouter",
      "description": "Fast, intelligent model for everyday tasks",
      "tags": ["chat", "code"],
      "inputCost": 0.003,
      "outputCost": 0.015,
      "contextWindow": 200000,
      "available": true
    }
  ],
  "count": 1,
  "openrouter": 1,
  "timestamp": "2026-03-19T00:00:00Z"
}

Errors

Code	Description
500	Failed to fetch models

List models by provider

GET /api/ai/models/:provider

No authentication required.

Path parameters

Parameter	Type	Description
provider	string	Provider 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

Field	Type	Required	Description
taskType	string	No	Type of task (default: general)

Response

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

Errors

Code	Description
404	No 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.

This endpoint requires a valid subscription plan. Requests without a recognized plan or active Stripe subscription receive a 402 response. The requested model must also be available on your plan — see plan-based model access below.

The chat endpoint uses header-based authentication. Access control is enforced through the x-user-plan and x-stripe-subscription-id headers rather than JWT verification. Admin emails (configured via ADMIN_EMAILS) bypass both plan and subscription requirements.

Request headers

The following headers are required for plan enforcement:

Header	Type	Required	Description
x-user-plan	string	Yes	Subscription plan name (label, solo, collective, or network)
x-user-email	string	No	User email. Admin emails bypass plan restrictions.
x-stripe-subscription-id	string	Yes	Active Stripe subscription ID

Request body

Field	Type	Required	Description
messages	array	Yes	Array of message objects with role (user, assistant, or system) and content
model	string	No	Model ID. Auto-selected based on taskType if omitted. Must be allowed by your plan.
taskType	string	No	Used for auto-selection when model is omitted
temperature	number	No	Sampling temperature
top_p	number	No	Nucleus sampling parameter
max_tokens	number	No	Maximum 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 a structured response with the following shape:

{
  "id": "chatcmpl-abc123",
  "model": "anthropic/claude-sonnet-4-20250514",
  "provider": "openrouter",
  "message": {
    "role": "assistant",
    "content": "Hello! How can I help you today?"
  },
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 10,
    "total_tokens": 35
  },
  "timestamp": "2026-03-19T00:00:00Z"
}

Errors

Code	Description
400	Messages array is required and must be non-empty
402	Valid subscription required. Returned when the plan header is missing or unrecognized (PLAN_REQUIRED), or when there is no active Stripe subscription (SUBSCRIPTION_REQUIRED).
403	Model not available on your plan (MODEL_RESTRICTED). The response includes an allowedModels array listing the models your plan supports.
404	No models available
429	Monthly token quota exceeded (QUOTA_EXCEEDED). See token quotas below.
500	AI provider error

402 error example

{
  "success": false,
  "error": "Valid subscription required. Choose a plan at /pricing",
  "code": "PLAN_REQUIRED"
}

403 error example

{
  "error": "Model openai/gpt-4-turbo not available on your plan. Upgrade for more models.",
  "code": "MODEL_RESTRICTED",
  "allowedModels": ["openai/gpt-4o-mini", "google/gemini-2.0-flash"]
}

429 error example

{
  "error": "Monthly token quota exceeded for plan \"solo\". Used 2,000,000 of 2,000,000 tokens. Quota resets at the start of next month.",
  "code": "QUOTA_EXCEEDED"
}

Token quotas

Each plan enforces a monthly token budget across all AI chat requests. Token usage (input + output) is tracked per user and checked before each request. When your usage reaches the plan limit, subsequent requests are rejected with a 429 status and a QUOTA_EXCEEDED error code. Quotas reset at the start of each calendar month.

Plan	Monthly token limit
solo	2,000,000
collective	6,000,000
label	20,000,000
network	Unlimited

The free plan has a token limit of zero. All agent usage requires a paid subscription.

Plan-based model access

Each subscription plan grants access to a specific set of AI models. The chat endpoint enforces these limits automatically.

Plan	Price	Models	Provision limit	Skill limit	A2A messages/day
label	£29/mo	openai/gpt-4o-mini, google/gemini-2.0-flash, xiaomi/mimo-v2-pro	1	3	100
solo	£79/mo	openai/gpt-4o-mini, openai/gpt-4o, google/gemini-2.0-flash, anthropic/claude-3.5-sonnet, xiaomi/mimo-v2-pro	3	10	500
collective	£199/mo	openai/gpt-4o-mini, openai/gpt-4o, openai/gpt-4-turbo, google/gemini-2.0-flash, anthropic/claude-3.5-sonnet, anthropic/claude-3-opus, xiaomi/mimo-v2-pro	10	25	2,000
network	£499/mo	All models	100	100	10,000

Admin users are automatically granted network-level access regardless of their subscription plan.

The plan middleware enforces model access based on the x-user-plan header. The label plan has the smallest model set (3 models) and is the entry-level tier designed for basic operations. The solo plan offers more models and a higher skill limit for individual users.

Model fallbacks

Each AI provider is configured with a primary model and a fallback model. When the primary model is unavailable or returns an error, the system automatically retries the request using the fallback model.

Provider	Primary model	Fallback model
openrouter	xiaomi/mimo-v2-pro	openrouter/anthropic/claude-sonnet-4, openrouter/google/gemini-2.5-flash
gemini	google/gemini-2.0-flash	openrouter/anthropic/claude-sonnet-4-5
groq	groq/gemma2-9b-it	openai/gpt-4o-mini
anthropic	anthropic/claude-sonnet-4-5	openai/gpt-4o
openai	openai/gpt-4o	openai/gpt-4o-mini

minimax (MiniMax/MiniMax-Text-01) is available in the provider configuration map but is not currently supported in the model fallback chain. It may be enabled in a future release.

Fallback routing is handled transparently. The response always indicates which model ultimately served the request via the model field.

Task-based model tiers

In addition to provider-level fallbacks, the backend AI service uses a tier-based routing system that selects models based on the type of work being performed. Each tier defines a primary model and two fallback models. If the primary model fails or times out, the system tries each fallback in order.

Tier	Primary model	Fallback models
reasoning	deepseek/deepseek-r1	meta-llama/llama-3.3-70b-instruct, moonshotai/kimi-k2.5
coding	qwen/qwen-2.5-coder-32b-instruct	deepseek/deepseek-r1, google/gemini-2.0-flash-001
fast	meta-llama/llama-3.3-70b-instruct	mistralai/mistral-7b-instruct, google/gemini-2.0-flash-001
creative	moonshotai/kimi-k2.5	deepseek/deepseek-r1, meta-llama/llama-3.3-70b-instruct

Each model attempt has a timeout of 30 seconds by default. You can override this with the AI_MODEL_TIMEOUT_MS environment variable. All tier-based requests are routed through OpenRouter.

Estimate cost

POST /api/ai/estimate-cost

Estimate the cost of a request based on token counts and model pricing.

Request body

Field	Type	Required	Description
model	string	Yes	Model ID
inputTokens	number	Yes	Number of input tokens
outputTokens	number	Yes	Number 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

Code	Description
400	Model, inputTokens, and outputTokens are all required