Compare
DeepSeek V3.2 vs …
Put models side by side on context, price, speed and availability.
| Model | |
|---|---|
| Overview | |
| Developer | DeepSeek |
| Context tokens | 160K |
| Max output tokens | 144K |
| Input | |
| Output | |
| Providers | 9 |
| Released | Dec 1, 2025 |
| Pricing | |
| Input per 1M | $0.26 |
| Output per 1M | $0.38 |
| Cache read per 1M | $0.13 |
| Performance | |
| Latency p50, median provider | 2.00s |
| Throughput p50, median provider | 25 tps |
| Uptime last 24h | 100.00% |
