All Vendors
Groq
FeaturedLLM Inference
Ultra-fast LLM inference powered by custom LPU hardware. The fastest API response times in the industry.
Visit Site
$0.05-2.70/1M tokens
Details
- Pricing Model
- usage-based
- Affiliate Program
- tbd
Specs
- input price per million
- 0.05
- max context
- 128K
- models
- Llama 3, Mixtral, Gemma
- output price per million
- 0.08
Fastest inference speeds available. Free tier generous for testing.