Groq

AI API · 8 facts · last checked 2026-10-05

https://groq.com

GroqCloud API

keyvalueplanstatusverifiedsource
ai.model.batch_apiyes“Batch API available with discounted pricing”api/developerstale2026-10-02GroqCloud rate limits
ai.model.context_window_tokens131,072 tokens“131k context window on Llama 3.3 70B”api/developerstale2026-10-02GroqCloud rate limits
api.rate_limit.requests_per_day14,400 requests/day“14,400 requests per day on the free tier”api/freestale2026-10-02GroqCloud rate limits
api.rate_limit.requests_per_minute30 requests/minute“30 requests per minute on the free tier”api/freestale2026-10-02GroqCloud rate limits
api.rate_limit.tokens_per_minute6,000 tokens/minute“6,000 tokens per minute on the free tier”api/freestale2026-10-02GroqCloud rate limits
api.rate_limit.tokens_per_minute300,000 tokens/minute“300,000 tokens per minute on the developer tier”api/developerstale2026-10-02GroqCloud rate limits
pricing.unit.input_tokens_per_millionUSD 0.59“$0.59 per million input tokens for Llama 3.3 70B”api/developerverified2026-10-05Groq pricing
pricing.unit.output_tokens_per_millionUSD 0.79“$0.79 per million output tokens for Llama 3.3 70B”api/developerverified2026-10-05Groq pricing

Agent view

GET /api/public/md/providers/groq
# Groq — limits, quotas, pricing and capabilities

Canonical site: https://groq.com
Facts: 8
Generated: 2026-10-07T02:48:31.565Z

| key | value | unit | plan | status | last_verified_at | source |
| --- | --- | --- | --- | --- | --- | --- |
| ai.model.batch_api | true |  | api/developer | stale | 2026-10-02T03:45:12.552+00:00 | https://console.groq.com/docs/rate-limits |
| ai.model.context_window_tokens | 131072 | tokens | api/developer | stale | 2026-10-02T03:45:12.552+00:00 | https://console.groq.com/docs/rate-limits |
| api.rate_limit.requests_per_day | 14400 | requests/day | api/free | stale | 2026-10-02T03:45:12.552+00:00 | https://console.groq.com/docs/rate-limits |
| api.rate_limit.requests_per_minute | 30 | requests/minute | api/free | stale | 2026-10-02T03:45:12.552+00:00 | https://console.groq.com/docs/rate-limits |
| api.rate_limit.tokens_per_minute | 6000 | tokens/minute | api/free | stale | 2026-10-02T03:45:12.552+00:00 | https://console.groq.com/docs/rate-limits |
| api.rate_limit.tokens_per_minute | 300000 | tokens/minute | api/developer | stale | 2026-10-02T03:45:12.552+00:00 | https://console.groq.com/docs/rate-limits |
| pricing.unit.input_tokens_per_million | 0.59 | USD | api/developer | verified | 2026-10-05T03:45:06.362+00:00 | https://groq.com/pricing |
| pricing.unit.output_tokens_per_million | 0.79 | USD | api/developer | verified | 2026-10-05T03:45:06.362+00:00 | https://groq.com/pricing |

Machine endpoints: /api/public/v1/providers/groq, /api/public/v1/facts?provider=groq