元任务 AI 网关 (Metask AI Gateway) is a unified AI API gateway that lets you access multiple large language models through a single, OpenAI-compatible API endpoint. Instead of juggling separate accounts and API keys for each AI provider, you connect once and route requests to any supported model.Documentation Index
Fetch the complete documentation index at: https://docs.metask.ai/llms.txt
Use this file to discover all available pages before exploring further.
Quick Start
Make your first AI API call in minutes using your gateway API key.
Authentication
Learn how to obtain and use your API key to authenticate requests.
Available Models
Browse all AI models available through the gateway.
API Reference
Full reference for the chat completions and models endpoints.
How it works
元任务 AI 网关 sits between your application and AI providers. You send requests to the gateway using the standard OpenAI API format, and the gateway routes them to the correct underlying model — handling authentication, rate limiting, and token accounting on your behalf.Create an account
Register at napi.origintask.cn to get access to the gateway.
Get your API key
Generate an API key from your dashboard. This key authenticates all your requests to the gateway.
Make your first call
Point your existing OpenAI-compatible code at the gateway endpoint and start using any supported model.
Key benefits
- Single endpoint — One base URL and one API key for all models, no per-provider setup needed.
- OpenAI-compatible — Drop-in replacement for the OpenAI API. Change the base URL and your existing code works.
- Multiple models — Access models from multiple AI providers through the same interface.
- Usage tracking — Monitor token consumption and costs in real time from your dashboard.
- Flexible billing — Top up your balance, use promo codes, or subscribe to a plan.
元任务 AI 网关 uses an OpenAI-compatible API format, meaning any library or tool that supports OpenAI’s API will work with the gateway by simply changing the
base_url.