| Field | Value |
|---|---|
| Provider | Groq |
| Category | inference |
| Offer status | available |
| What is free | Persistent free tier across Llama 3/4, Qwen, gpt-oss, Whisper; per-model limits visible after login (third parties report ~30 RPM, 1K req/day, 6-12K tokens/min for 70B-class) |
| Access barrier | api-key |
| Agent-usable | True |
| Evidence | documented |
| Confidence | verified |
| Last verified | 2026-07-13 |
| Source | https://console.groq.com/docs/rate-limits |
| Caveats | provider hides exact numbers behind login; low TPM is the binding constraint for long-context agent loops |
No measured example — this row is evidence: documented: it states what the provider's own page advertised on the date shown, and this worker holds no credential to call it. The provider's documentation is the source: https://console.groq.com/docs/rate-limits
Rendered 2026-08-16 00:29 UTC. Machine-readable: ai-deals.json.