DeepSeek: DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flashDeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.
Providers
16 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.04 | $1.28 | $0.04 | 0.65s | 94 tps | 100% | |
| $0.09 | $0.18 | $0.02 | 1.49s | 53 tps | 100% | |
 DigitalOcean | $0.10 | $0.20 | $0.02 | 0.84s | 25 tps | 100% |
| $0.14 | $0.28 | $0.07 | 1.00s | 39 tps | 100% | |
| $0.10 | $0.19 | $0.02 | 2.83s | 21 tps | 99.95% | |
| $0.15 | $0.30 | $0.03 | 1.19s | 85 tps | 99.84% | |
 DeepInfraus · fp8 | $0.09 | $0.18 | $0.02 | 2.49s | 20 tps | 99.19% |
 SiliconFlowfp8 | $0.13 | $0.28 | $0.03 | 1.35s | 48 tps | 99.07% |
 Azureeastus2 | $0.21 | $0.56 | $0.03 | 3.25s | 49 tps | 98.94% |
| $0.07 | $0.14 | $0.01 | 1.18s | 45 tps | 98.8% | |
| $0.03 | $1.15 | $0.01 | 1.68s | 15 tps | 98.16% | |
| $0.14 | $0.28 | $0.03 | 2.28s | 51 tps | 96.94% | |
| $0.04 | $0.08 | $0.01 | 0.95s | 66 tps | 96.49% | |
| $0.19 | $0.50 | Variable | 1.60s | 22 tps | 95.59% | |
| $0.43 | $0.17 | $0.01 | 0.78s | 45 tps | 95.3% | |
| $0.44 | $1.32 | $0.01 | 1.81s | 53 tps | 94.11% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves DeepSeek V4 Flash 0423 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what DeepSeek V4 Flash 0423 costs pay-as-you-go elsewhere, not what you pay here.
Performance
Time to first token and output speed across every provider, over the last 3 days.
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Apps
Tools that most often run DeepSeek V4 Flash 0423, by tokens this week.
Activity
14694.3B tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.
