Groq free plan

Groq (GroqCloud) Free API tier

The catch: The free plan allows only 8K tokens per minute on the main chat models, far below their 131K context, and Groq may log inputs and outputs for up to 30 days for reliability or abuse checks unless you turn on Zero Data Retention.

Access	Free API tier
Free limits	Free Plan, per organization: openai/gpt-oss-120b, openai/gpt-oss-20b, openai/gpt-oss-safeguard-20b and qwen/qwen3.8-27b: 30 RPM, 1K RPD, 8K TPM, 200K TPD each. meta-llama/llama-prompt-guard-2-22m and -86m: 30 RPM, 14.4K RPD, 15K TPM, 500K TPD. canopylabs/orpheus-v1-english and canopylabs/orpheus-arabic-saudi (text to speech): 10 RPM, 100 RPD, 1.2K TPM, 3.6K TPD. whisper-large-v3 and whisper-large-v3-turbo: 20 RPM, 2K RPD, 7.2K audio seconds/hour, 28.8K audio seconds/day. Cached tokens do not count toward limits. Llama 3.1 8B, Llama 3.3 70B and MiniMax M2.7 are now Enterprise-only (contact sales) and not on the free plan.
Modality	text, code, audio
Credit card	Not required
Commercial use	Allowed
Trains on your data	No
Licence or terms	Groq Services Agreement (last modified 22 Jun 2026)
Context window	131,072 tokens
Model id	`openai/gpt-oss-120b`
Base URL	`https://api.groq.com/openai/v1`
Last checked	2 Oct 2026

How to use gpt-oss-120b, Qwen3.8 27B

It speaks the OpenAI API at https://api.groq.com/openai/v1, so the OpenAI SDK you already use works once you change the base URL and key.

Quickstart

curl https://api.groq.com/openai/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer $KEY" -d '{"model":"openai/gpt-oss-120b","messages":[{"role":"user","content":"Hello"}]}'

Paste into Claude Code

I want to use the free AI model "gpt-oss-120b, Qwen3.8 27B" from Groq (model id: openai/gpt-oss-120b) in my project.
Please:
1. Check the provider docs and give me the exact steps to get a free API key.
2. Give me a minimal working example that reads the key from an environment variable.
3. Tell me the real free limits and any catch (commercial use, card, data use). Listed limits: 30 RPM, 1K requests and 200K tokens a day per model.
4. If the same provider has a more generous free option, mention it.

Provider docs Get a free key Compare all 43 free options

Before you ship on it

The free plan allows only 8K tokens per minute on the main chat models, far below their 131K context, and Groq may log inputs and outputs for up to 30 days for reliability or abuse checks unless you turn on Zero Data Retention.
Groq Services Agreement (last modified 22 Jun 2026) governs GroqCloud 'for developers, businesses, or enterprise organizations' and says the services 'are not for consumer use'; no free-plan restriction on commercial…
Free tiers are shared capacity: treat the limits as a ceiling, not a promise, and keep a paid fallback.

Questions

Is Groq free plan free?

Yes. Groq offers it as free api tier, with these limits: 30 RPM, 1K requests and 200K tokens a day per model. No credit card is needed.

Can I use Groq free plan commercially?

Yes, under Groq Services Agreement (last modified 22 Jun 2026). Check the current terms before you ship.

How do I start with Groq free plan?

It speaks the OpenAI API at https://api.groq.com/openai/v1, so the OpenAI SDK you already use works once you change the base URL and key.

Source: console.groq.com/docs/rate-limits, checked 2 Oct 2026.