For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
DocsAPI ReferenceSDKs
DocsAPI ReferenceSDKs
  • Introduction
    • Product Overview
    • Pricing
    • Model Explanation
    • Available Models
  • Guides
    • Quickstart
    • Authentication
    • BYOK
    • Dashboard Guide
    • Prompt Templates
    • Embeddings
    • RAG (Files & Search)
    • Audio
    • Images & Vision
    • Image Generation
    • Compare
    • Batch API
    • Auto Routing
    • Realtime Audio
  • SDKs
    • Node.js (TypeScript)
    • Python
    • Go
  • Infrastructure
    • Architecture
LogoLogo
On this page
  • Product Overview
  • Features
  • How It Works
Introduction

Product Overview

||View as Markdown|
Was this page helpful?
Edit this page
Next

Pricing Details

Built with

Product Overview

MeshAPI is an AI model gateway that gives you instant access to a massive variety of LLMs through a single, unified API. Whether you’re building simple chatbots or complex multi-agent architectures, MeshAPI allows you to seamlessly switch between models without changing your code structure.

Features

  • One Universal API: Code once. A single ChatCompletion API request works for over 250+ different base models.
  • Unified Billing: Avoid managing dozens of subscriptions. Deposit funds into one account and consume any model.
  • Provider Fallbacks: If a specific model or provider experiences downtime, the gateway can automatically fall back to another supported mechanism to ensure reliable inferences.
  • Built-in Rate Limiting: Prevent run-away costs by applying robust rate limiting to your models and integrations.
  • Prompt Templates: Manage, version, and share prompts effectively via our secure templating system.

How It Works

  1. Authentication: Create a single API Key (or Data-Plane Key).
  2. Integration: Replace the Base URL of any OpenAI-compatible SDK with https://api.meshapi.ai.
  3. Execution: Pass the Model ID and standard parameters as you normally would. Your request is transparently routed out to the underlying host.

Enjoy the developer experience you already know, upgraded with universal model access.