> ## Documentation Index
> Fetch the complete documentation index at: https://docs.meshai.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Proxy Overview

> Zero-code monitoring: one env var, full observability

The MeshAI proxy is a transparent LLM API gateway that sits between your agents and LLM providers. It provides:

* **Automatic token tracking**: every request's tokens and cost recorded
* **Governance enforcement**: policies evaluated in real-time (\<5ms overhead)
* **No code changes**: just change one environment variable

## How It Works

```
Your Agent → MeshAI Proxy → LLM Provider (OpenAI, Anthropic, etc.)
                 ↓
          Token tracking
          Cost attribution
          Policy enforcement
          Anomaly detection
```

## Supported Providers

| Provider      | Base URL                                |
| ------------- | --------------------------------------- |
| Anthropic     | `https://proxy.meshai.dev/v1/anthropic` |
| OpenAI        | `https://proxy.meshai.dev/v1/openai`    |
| NVIDIA        | `https://proxy.meshai.dev/v1/nvidia`    |
| Google Vertex | `https://proxy.meshai.dev/v1/vertex`    |
| AWS Bedrock   | `https://proxy.meshai.dev/v1/bedrock`   |

## Key Features

* **Pass-through**: Responses are identical to direct provider calls
* **Streaming**: Full SSE streaming support
* **No content storage**: MeshAI never stores prompt or completion text
* **Fail-safe**: If the proxy is unavailable, configure your agent to fall back to direct provider URLs