Groq

Groq

unknown

Groq-hosted GPT-OSS and Qwen models with a recurring free developer tier. Organization-level request and token limits apply.

https://api.groq.com/openai/v1

Last Probe Latency

—

Healthy Observed Days

—

Rate Limits

30 RPM / 1,000 RPD

Sign-up Required

Yes

Provider status summarizes sampled models checked with the monitoring account. Your access and limits may differ.

Documentation checked: . Model availability is subject to the provider's current catalog.

Listed chat models: 30 RPM, 1,000 RPD, 8,000 TPM and 200,000 TPD on the free plan. Exact account limits can differ. Older Llama models are now marked Enterprise in the official catalog.

Info

Base URLhttps://api.groq.com/openai/v1
Sign-up RequiredYes
Credit CardNot verified
Context Window131072
Last Verified2026-11-16
fast-inferenceopenai-compatiblellamafunction-call

Models(3)

Model health is unknown until an actual check completes.

openai/gpt-oss-120b

Context: 131072 · 30 RPM · $0.150/$0.600 per 1M

unknown

openai/gpt-oss-20b

Context: 131072 · 30 RPM · $0.075/$0.300 per 1M

unknown

qwen/qwen3.8-27b

Context: 131072 · 30 RPM · $0.800/$4 per 1M

unknown

Quick Start

bash
export API_KEY="your_api_key_here"
curl 'https://api.groq.com/openai/v1/chat/completions' \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "openai/gpt-oss-120b",
    "messages": [
      {
        "role": "user",
        "content": "Hello! How are you?"
      }
    ]
  }'