Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM
GroqCloud · Free tier

Groq API free tier

Groq publishes sample Free-plan limits per model, applied at the organisation level, and says the current exact limits for an organisation are on the limits page in account settings, with possible exceptions. Text models such as gpt-oss-120b and Qwen3.8 27B list 30 requests a minute, 1,000 requests a day, 8,000 tokens a minute and 200,000 tokens a day.

Read from the provider page

Free tier: GroqCloud API, Free plan

Published on the provider page
GroqCloud API, Free plan: each limit with its value, scope and note.
LimitValueApplies toNote
Requests per minute30openai/gpt-oss-120bFree plan sample limit
Requests per day1,000openai/gpt-oss-120bFree plan sample limit
Tokens per minute8,000openai/gpt-oss-120bFree plan sample limit
Tokens per day200,000openai/gpt-oss-120bFree plan sample limit
Requests per minute30qwen/qwen3.8-27bFree plan sample limit
Requests per day1,000qwen/qwen3.8-27bFree plan sample limit
Tokens per minute8,000qwen/qwen3.8-27bFree plan sample limit
Tokens per day200,000qwen/qwen3.8-27bFree plan sample limit
Requests per minute30groq/compoundFree plan sample limit
Requests per day250groq/compoundFree plan sample limit
Tokens per minute70,000groq/compoundFree plan sample limit
What moves you past this tier
Upgrading to the Developer plan gives higher limits plus Batch and Flex processing; enterprise limits are available for select workloads.
Card required
Not stated by the provider
Source
Groq rate limits Read 2026-09-14

Limits apply per organisation, not per user; the docs table is a sample and the console limits page is authoritative.

Questions

Is the Groq API free?

GroqCloud has a Free plan. Groq publishes sample limits per model for it: 30 requests a minute, 1,000 requests a day, 8,000 tokens a minute and 200,000 tokens a day on text models such as gpt-oss-120b and Qwen3.8 27B, with the Compound systems at 30 requests a minute and 250 a day.

Are Groq rate limits per user or per organisation?

Per organisation. Groq states that rate limits apply at the organisation level, not to individual users, so extra keys or members do not add capacity. The documentation table is a sample; the exact current limits for an organisation are on the limits page in account settings, and Groq notes there may be exceptions.

What does the Groq Developer plan change?

Groq says upgrading to the Developer plan gives access to higher limits plus Batch and Flex processing, and that higher limits are available for select workloads and enterprise use cases. The plan’s price and whether a card is required are not stated on the rate-limits page we read, so we do not record them.