Compare
DeepSeek V4.1 Flash (batch) vs …
Put models side by side on context, price, speed and availability.
| Model | |
|---|---|
| Overview | |
| Developer | DeepSeek |
| Context tokens | 1M |
| Max output tokens | 375K |
| Input | |
| Output | |
| Providers | 34 |
| Released | Sep 10, 2026 |
| Pricing | |
| Input per 1M | $0.05 |
| Output per 1M | $0.15 |
| Cache read per 1M | $0.00 |
| Performance | |
| Latency p50, median provider | 0.72s |
| Throughput p50, median provider | 92 tps |
| Uptime last 24h | 100.00% |
