G
Groq
groq
· 6 models · synced never
Ultra-low-latency LPU inference for open models.
| Model | Type | Input $/MTok | Output $/MTok | Context | Upstream ID |
|---|---|---|---|---|---|
| Llama 3.1 8B Instruct meta-llama | LLM | $0.05 | $0.08 | 131K | meta-llama/llama-3.1-8b-instruct |
| gpt-oss-20b (batch) openai | LLM | $0.075 | $0.3 | 131K | openai/gpt-oss-20b |
| gpt-oss-safeguard-20b openai | LLM | $0.075 | $0.3 | 131K | openai/gpt-oss-safeguard-20b |
| gpt-oss-120b (batch) openai | LLM | $0.15 | $0.6 | 131K | openai/gpt-oss-120b |
| Llama 3.3 70B Instruct meta-llama | LLM | $0.59 | $0.79 | 131K | meta-llama/llama-3.3-70b-instruct |
| MiniMax M2.7 minimax | LLM | $0.6 | $1.80 | 197K | minimax/minimax-m2.7 |