Groq · LLM API · Free tier
GPT-OSS 120B on Groq (Free plan)
Last checked 22 Oct 2026 · ID groq.gpt-oss-120b
Some limits below come from third-party snapshots, not the provider's own docs. Check the provider's page before you rely on them.
Limits
| Limit | Value | Reset | Checked | Source |
|---|---|---|---|---|
| Requests per minute · per organization | 30 | rolling window | 22 Oct 2026 | dev.to Third-party snapshot |
| Requests per day · per organization | 1,000 | reset not published | 22 Oct 2026 | dev.to Third-party snapshot |
| Tokens per minute · per organization The 8K tokens/minute cap is usually the first one hit. | 8,000 | rolling window | 22 Oct 2026 | dev.to Third-party snapshot |
| Tokens per day · per organization | 200,000 | reset not published | 22 Oct 2026 | dev.to Third-party snapshot |
Models
openai/gpt-oss-120b
Endpoint (openai compatible): https://api.groq.com/openai/v1
Notes
Groq publishes sample Free-plan limits; an organization's exact limits are on its Limits page. Every response carries x-ratelimit-* headers, so the router can read live remaining values.
Sources
- dev.to · Third-party snapshot · fetched 7 Nov 2026
- console.groq.com · Official docs · fetched 8 Nov 2026