DeepSeek: DeepSeek V4 Flash
Reasoning / thinkingJSON Schema output
Supported by some available channels. Routing filters by the requested capabilities.High-throughput lane optimized for fast turnaround and cost efficiency.
Capability support
Context window1Mtokens
Official pricing
The model's published list prices, used only as the comparison baseline for route pricing and discounts
Current official windowBase windowAsia/Shanghai
Input tokens¥1.001M
Output tokens¥4.001M
Cache read¥0.021M
Cache write¥0.00001M
Full time-based pricing
| Price window | Applies during | Input tokens1M | Output tokens1M | Cache read1M | Cache write1M |
|---|---|---|---|---|---|
| Other hoursCurrent | When no special window matches · Asia/Shanghai | ¥1.00 | ¥4.00 | ¥0.02 | ¥0.0000 |
| Peak Hours | Every day · 09:00–12:00 · Asia/Shanghai | ¥2.00 | ¥8.00 | ¥0.04 | ¥0.0000 |
| Peak Hours | Every day · 14:00–18:00 · Asia/Shanghai | ¥2.00 | ¥8.00 | ¥0.04 | ¥0.0000 |
Available routes
Provider, public group, live pricing, latency, and uptime per active route
Provider / groupInput tokens1MOutput tokens1MCache read1MLatencyThroughputUptime
DeepSeekGroup: DeepSeek V4 FlashCurrent sale window: Base window · Asia/Shanghai
Input tokens$0.18
Output tokens$0.71
Cache read$0.0036
Latency0.9sThroughput10.1 t/s
Uptime100.0%