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 |
|---|---|---|---|---|---|---|
| $0.09 | $0.18 | $0.02 | 2.03s | 53 tps | 100% | |
| $0.05 | $0.45 | $0.05 | 0.64s | 76 tps | 100% | |
| $0.14 | $0.28 | $0.07 | 0.82s | 50 tps | 100% | |
| $0.08 | $0.17 | $0.02 | 2.47s | 32 tps | 100% | |
 DigitalOcean | $0.10 | $0.20 | $0.02 | 0.83s | 25 tps | 100% |
| $0.70 | $0.17 | $0.01 | 0.71s | 62 tps | 100% | |
| $0.44 | $1.32 | $0.01 | 1.67s | 58 tps | 100% | |
| $0.15 | $0.30 | $0.03 | 1.27s | 74 tps | 100% | |
| $0.10 | $0.19 | $0.02 | 1.32s | 48 tps | 99.97% | |
 SiliconFlowfp8 | $0.13 | $0.28 | $0.03 | 1.14s | 44 tps | 99.86% |
| $0.14 | $0.28 | $0.03 | 3.57s | 36 tps | 99.86% | |
 DeepInfraus · fp8 | $0.09 | $0.18 | $0.02 | 4.74s | 14 tps | 99.74% |
| $0.04 | $0.14 | $0.01 | 1.63s | 12 tps | 99.4% | |
 Azureeastus2 | $0.21 | $0.56 | $0.03 | 1.41s | 68 tps | 97.82% |
| $0.14 | $0.28 | $0.03 | 0.88s | 118 tps | 97.25% | |
| $0.19 | $0.50 | Variable | 1.06s | 34 tps | 87.25% |
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
13661.8B tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.
