# Groq API

Category: [AI models and chat](https://free-web-services.com/web-services/ai/llm/)  
Page: https://free-web-services.com/web-services/ai/llm/groq-api.html  
Documentation: https://console.groq.com/docs/overview

Groq runs open AI models on its own LPU chips, which makes responses very fast. The API offers chat and text generation with open models (such as Llama, Qwen and GPT-OSS), speech-to-text with Whisper and text-to-speech, and is compatible with the OpenAI API format, so existing code often works by changing the base URL. Responses are JSON. Free plan with a free API key and rate limits per model; paid plans for higher limits. An official MCP server (groq-mcp) lets AI agents call models hosted on Groq.

- API key: Needed, free
- Pricing: Free plan with a free API key and rate limits per model; paid plans for higher limits.
- From the browser: Yes (CORS)
- Formats: JSON
- Interface: REST, MCP
- Provider: console.groq.com
- Last checked: Working on November 1st, 2026

Example request:

```sh
curl -X POST 'https://api.groq.com/openai/v1/chat/completions' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "llama-3.1-8b-instant", "messages": [{"role": "user", "content": "hello"}]}'
```

Replace YOUR_API_KEY with your own key. The JavaScript works in a web page as well as in Node.js 18 or newer.