.
Groq models on Manifest
1M tokens
/ 30 days
9 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.Llama 4 Scout 17b 16e Instruct | API Key | 427 K |
2.Gpt Oss 20b | API Key | 297 K |
3.Gpt Oss 120b | API Key | 88 K |
4.Llama 3.1 8b Instant | API Key | 85 K |
5.Qwen3.6 27b | API Key | 80 K |
6.Qwen3 32b | API Key | 48 K |
7.Llama 3.3 70b Versatile | API Key | 15 K |
8.Gpt Oss Safeguard 20b | API Key | 1 K |
9.Allam 2 7b | API Key | 573 |
