Groq Free Tier
- Free token amount
- Per-model rate limits, e.g. 30 RPM / 1K-14.4K RPD / 8K-500K TPM
- Duration
- No expiration
- Expiry date
- No fixed end date
- Verified
- Sep 12, 2026
Overview
Groq runs open-weight models on its LPU inference hardware and serves them through an OpenAI-compatible API. New accounts begin on the Free plan, which provides rate-limited access to the hosted models without a paid subscription.
Free Tier Quotas & Limits
Published free/base per-model limits include:
| Model ID | RPM | RPD | TPM | TPD |
|---|---|---|---|---|
| openai/gpt-oss-120b | 30 | 1K | 8K | 200K |
| openai/gpt-oss-20b | 30 | 1K | 8K | 200K |
| openai/gpt-oss-safeguard-20b | 30 | 1K | 8K | 200K |
| qwen/qwen3.6-27b | 30 | 1K | 8K | 200K |
| qwen/qwen3.8-27b | 30 | 1K | 8K | 200K |
| groq/compound | 30 | 250 | 70K | — |
| groq/compound-mini | 30 | 250 | 70K | — |
| meta-llama/llama-prompt-guard-2-22m | 30 | 14.4K | 15K | 500K |
| whisper-large-v3 | 20 | 2K | — | — |
| whisper-large-v3-turbo | 20 | 2K | — | — |
Limits apply at the organization level rather than per user, cached tokens do not count toward them, and exceeding any metric returns HTTP 429. Exact current limits for an account are shown on its limits page.
Key Free Models
The free catalog covers text generation and reasoning (openai/gpt-oss-120b, openai/gpt-oss-20b, qwen/qwen3.6-27b, qwen/qwen3.8-27b), agentic systems with built-in web search and code execution (groq/compound, groq/compound-mini), content moderation (meta-llama/llama-prompt-guard-2-22m) and speech-to-text (whisper-large-v3, whisper-large-v3-turbo).
How to Get Started
Sign up at console.groq.com, create a key on the API Keys page, and call https://api.groq.com/openai/v1/chat/completions. The endpoint works with the official OpenAI SDKs by changing the base URL and key, and Groq also publishes its own Python SDK. Higher limits are available by upgrading to the Developer plan.
More free API credits
Browse all free API credits - Free AI API credits, re-verified weekly.