Build automations
Bring AI into flow
Extend your stack
Operate with control
Revenue & customer teams
Ops & internal systems
Work in your terminal
Context that lasts
Beyond your code
Ship your changes
Make it yours
Llama 3.3 70B quantized to fp8 precision, optimized to be faster.
puqai/meta/llama-3.3-70b-instruct-fp8-fast
| Rate | Price | Per |
|---|---|---|
| Input | $0.3663 | 1M |
| Output | $2.82 | 1M |