---
title: "Provider API Docs"
source: https://docs.autohand.ai/getting-started/plans-and-pricing/provider-api
---

# Provider API

Autohand provides an OpenAI-compatible Chat Completions endpoint. To use an existing compatible client, update its base URL and API key.

## Calling the API

Create an API key from the **API Keys** page in the console. Each key is shown only once, so copy and store the key securely when it is created.

```
curl https://api.autohand.ai/v1/chat/completions \
  -H "Authorization: Bearer $AUTOHAND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "fantail",
    "messages": [{"role": "user", "content": "Explain this stack trace"}]
  }'
```

Use `fantail` or `moa` as the model identifier, depending on your plan. See [Available models](https://docs.autohand.ai/getting-started/plans-and-pricing/available-models) for the full access comparison.

## Share account usage

Autohand Code, the Agent SDK, and direct API calls share the same account allowance. A message used through the API counts toward the same limits as a message used in your editor.

The per-minute request limit also applies to API calls:

-   Free: 10 requests per minute
-   Pro and Team: 100 requests per minute
-   Max: 200 requests per minute
-   Enterprise: 400 requests per minute

This is typically the first limit that high-volume automation reaches.

## Bring your own provider

Autohand Code can also connect to an external provider, including OpenRouter, OpenAI, DeepSeek, Cerebras, Azure AI Foundry, Google Cloud Vertex AI, and local runtimes such as Ollama, MLX, and llama.cpp.

When you use your own provider, that provider bills you directly and Autohand message limits do not apply to those requests. Your Autohand plan and limits continue to apply whenever you use Autohand-hosted models.