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
17 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.05 | $0.45 | $0.05 | 0.72s | 85 tps | 100% | |
| $0.60 | $0.17 | $0.20 | 0.31s | 159 tps | 100% | |
| $0.44 | $1.32 | $0.01 | 1.88s | 55 tps | 100% | |
| $0.08 | $0.17 | $0.02 | 3.46s | 22 tps | 100% | |
| $0.14 | $0.28 | $0.03 | 0.65s | 61 tps | 100% | |
| $0.14 | $0.28 | $0.03 | 2.69s | 37 tps | 99.95% | |
 DeepInfraus · fp8 | $0.09 | $0.18 | $0.02 | 3.12s | 20 tps | 99.92% |
| $0.14 | $0.28 | $0.03 | 0.89s | 125 tps | 99.92% | |
| $0.10 | $0.19 | $0.02 | 1.51s | 30 tps | 99.87% | |
 DigitalOcean | $0.10 | $0.20 | $0.02 | 1.01s | 19 tps | 99.82% |
| $0.14 | $0.28 | $0.07 | 1.44s | 51 tps | 99.82% | |
| $0.19 | $0.50 | Variable | 7.07s | 19 tps | 99.79% | |
| $0.09 | $0.18 | $0.02 | 1.63s | 46 tps | 99.72% | |
 SiliconFlowfp8 | $0.13 | $0.28 | $0.03 | 1.27s | 37 tps | 99.27% |
 Azureeastus2 | $0.21 | $0.56 | $0.03 | 1.29s | 91 tps | 99.02% |
 Fireworks | $0.10 | $0.21 | $0.02 | 1.04s | 55 tps | 88.86% |
| $0.15 | $0.30 | $0.03 | — | — | 8.31% |
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
12796.2B tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.
