Groq

Provider

Low-latency inference API for open LLMs and Whisper

Price: Free tier, then paid
Access: API key

Docs
llms.txt

About

GroqCloud runs open models such as GPT-OSS, Qwen and Whisper on Groq's inference cloud behind an OpenAI-compatible API. It is for apps that need very fast token output. Its model list is short compared with larger hosts.

What you can do with it

Run GPT-OSS and Qwen models with very low latency
Transcribe audio fast with Whisper Large v3 Turbo
Switch from OpenAI by changing the base URL to Groq

Get started

Create an API key in the GroqCloud console
Set GROQ_API_KEY in your environment

Example

curl -X POST https://api.groq.com/openai/v1/responses \
  -H "Authorization: Bearer $GROQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-oss-20b",
    "input": "Explain the importance of fast language models"
  }'

Details

Hosting: Hosted service
Available in: Worldwide
Official SDKs: Python, JavaScript/TypeScript
MCP server: None