Llama-3.3-70B-Instruct
by meta-llama
text-generation · 2.7k likes · 587.4k downloads
Inference providers
| Provider | $/1M in | $/1M out | Throughput |
|---|---|---|---|
| Groq | 295 tok/s | ||
| Novita | 27 tok/s | ||
| SambaNova | 281 tok/s | ||
| Nscale | 16 tok/s | ||
| Hyperbolic | 72 tok/s | ||
| Together AI | 108 tok/s | ||
| Fireworks | 109 tok/s | ||
| Scaleway | 81 tok/s | ||
| OVHcloud | 30 tok/s |