Search models, providers, and docs
llama-3.3-70b-instruct-fp8-fast is available from 4 providers. The lowest input price is $0.293 per million tokens from AIgateway. It supports up to 24K tokens of context.
| AIgateway | meta/llama-3.3-70b-instruct-fp8-fast | $0.293 | $2.253 | - | 24K | 8.2K |
| Cloudflare AI | @cf/meta/llama-3.3-70b-instruct-fp8-fast | $0.293 | $2.253 | - | 24K | - |
| Eden AI | cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast | $0.293 | $2.253 | - | 24K | - |
| TrustedRouter | meta-llama/llama-3.3-70b-instruct-fp8-fast | $0.3091 | $2.3769 | - | 24K | - |