Free
$0/month
- - all Free Tier benefits
- - Tinyllama ~80 tokens/s
- - Llama-3-8b ~550 tokens/s
- - Llama-3.1-8b ~350 tokens/s
- - Llama-3.2-1b ~260 tokens/s
- - Llama-3-70b ~140 tokens/s
- - Llama-3.3-70b ~400 tokens/s
- - Gemma-7b-it ~300 tokens/s
- - stable diffusion
- - Unlimited api calls
- - direct developer support (when available)
- - stable speeds and uptime
- - second fastest inference speeds in the world