Compare
Llama 3.3 70B Instruct vs …
Put models side by side on context, price, speed and availability.
| Model | |
|---|---|
| Overview | |
| Developer | Meta |
| Context tokens | 128K |
| Max output tokens | 32K |
| Input | |
| Output | |
| Providers | 11 |
| Released | Dec 6, 2024 |
| Pricing | |
| Input per 1M | $0.59 |
| Output per 1M | $0.79 |
| Cache read per 1M | $0.29 |
| Performance | |
| Latency p50, median provider | 0.73s |
| Throughput p50, median provider | 50 tps |
| Uptime last 24h | 100.00% |
