Ultra-fast inference on GroqCloud
| Model | API ID | Release | Cutoff | Conf. | Status | Notes |
|---|---|---|---|---|---|---|
| Llama 3.1 8B (Groq) | llama-3.1-8b-instant |
2024-07 | 2023-12 | medium | active | Hosted on GroqCloud. 131k context. ~560 t/s. |
| Llama 3.3 70B (Groq) | llama-3.3-70b-versatile |
2024-12 | 2023-12 | medium | active | Hosted on GroqCloud. 131k context. ~280 t/s. |
| GPT-OSS 120B (Groq) | openai/gpt-oss-120b | 2025-08 | 2025-06 | low | active | OpenAI open-weight model. 131k context. ~500 t/s. |
| GPT-OSS 20B (Groq) | openai/gpt-oss-20b | 2025-08 | 2025-06 | low | active | Smaller open-weight model. 131k context. ~1000 t/s. |
| Llama 4 Scout (Groq) | meta-llama/llama-4-scout-17b-16e-instruct | 2025-04 | 2024-08 | medium | active | Preview on Groq. 131k context. ~750 t/s. |
| Qwen3-32B (Groq) | qwen/qwen3-32b | 2025-04 | 2025-01 | low | preview | Preview on Groq. 131k context. ~400 t/s. |
| Qwen3.6-27B (Groq) | qwen/qwen3.6-27b | 2026-06 | Unknown | low | preview | Preview on Groq. 131k context. ~500 t/s. |
Knowledge Cutoffs