Groq models on Manifest
310K tokens
/ 30 days
7 models routed through Manifest over the last 30 days.
Groq runs open models like Llama and Qwen on its LPU engine for ultra-low latency. Route Groq through Manifest with a spending cap and fallback.
Groq tokens processed on Manifest
Models in use
# Model |
Auth type | Tokens / last 30 days |
|---|---|---|
1.Gpt Oss 120b | API Key | 234 K |
2.Qwen3.6 27b | API Key | 37 K |
3.Qwen3.8 27b | API Key | 22 K |
4.Llama 3.3 70b Versatile | API Key | 12 K |
5.Llama 3.1 8b Instant | API Key | 2 K |
6.Gpt Oss 20b | API Key | 2 K |
7.Gpt Oss Safeguard 20b | API Key | 776 |
