API Reference

MR Multi Model AI Coder provides a REST API for sending messages, listing models, checking quotas, and counting tokens — through a unified interface that works with multiple AI providers.

Base URL: https://api.mr-coder.io (or your self-hosted instance)

POST/v1/messages

Messages

Send a message and receive an AI response. Supports streaming, system prompts, and tool use.

GET/v1/models

Models

List all available models with their IDs, context windows, and pricing tiers.

GET/v1/key-status

Key Status

Check your API key validity, rate limits, token window usage, and monthly budget.

POST/v1/messages/count_tokens

Count Tokens

Calculate the token count for a given messages payload before sending a request.

Base URL

Bash

https://api.mr-coder.io

All API endpoints are relative to this base URL. For local development or self-hosting, replace the domain with your own instance URL.

Authentication

Authenticate requests using your API key via the x-api-key header:

Bash

curl https://api.mr-coder.io/v1/models \
  -H "x-api-key: sk-mr-auth-xxxxxxxxxxxxxxxxxxxxxxxxxxxx"

For full authentication details including key types, session auth, and multi-key strategies, see the Authentication guide.

Request Format

All request bodies must be JSON with Content-Type: application/json header.

Error Responses

Errors follow the Anthropic format with a type and message:

JSON

{
  "type": "error",
  "error": {
    "type": "authentication_error",
    "message": "Invalid API key. Please check that your API key is correct and try again."
  }
}

HTTP Status	Error Type
400	invalid_request_error
401	authentication_error
403	permission_error
429	rate_limit_error
500	api_error

Rate Limits

Rate limits are enforced per API key and vary by plan. Check your current limits with the Key Status endpoint.

Limit Type	Description
RPM (Requests Per Minute)	Maximum requests per minute for your key tier.
Token Window	Rolling window of token usage (e.g. 1M tokens per 5 hours).
Monthly Budget	Optional monthly token cap. Resets on the 1st of each month.

Provider Prefix Format

Model IDs can be bare (e.g., claude-sonnet-4-6) or prefixed with the provider (e.g., anthropic:claude-sonnet-4-6). Bare names default to anthropic:.

JSON

# Both of these are equivalent:
"model": "claude-sonnet-4-6"
"model": "anthropic:claude-sonnet-4-6"

Authentication Guide →Key types, headers, and auth strategies