Groq
Inference host · 5 models · 5 priced routes · groq.com
Models on Groq
| Model | In / out per 1M | Vs headline |
|---|---|---|
| Llama 3.1 8B Instruct Groq | $0.05 / $0.08+130% vs headline | +130% |
| gpt-oss-safeguard-20b Groq | $0.075 / $0.3Same vs headline | Same |
| gpt-oss-20b Groq | $0.075 / $0.3+265% vs headline | +265% |
| gpt-oss-120b Groq | $0.15 / $0.6+304% vs headline | +304% |
| Llama 3.3 70B Instruct Groq | $0.59 / $0.79+313% vs headline | +313% |
About Groq
Batch: 50% cost discount compared to synchronous APIs (console.groq.com/docs/batch); does not stack with prompt caching
Caching: There is a 50% discount for cached input tokens (console.groq.com/docs/prompt-caching)
Across fru.devCompany profileAcquisition by NVIDIA (2025)
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.