DeepSeek: DeepSeek V4 Pro 0423
deepseek/deepseek-v4-proDeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.
Providers
15 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.43 | $0.86 | $0.04 | 0.97s | 62 tps | 100% | |
 DeepInfraus · fp8 | $1.30 | $2.60 | $0.10 | 1.59s | 38 tps | 100% |
 DigitalOcean | $1.04 | $2.09 | $0.21 | 2.84s | 5 tps | 99.97% |
| $1.68 | $3.38 | $0.13 | 1.57s | 40 tps | 99.97% | |
| $1.60 | $3.20 | $0.14 | 2.01s | 55 tps | 99.92% | |
| $1.56 | $3.12 | $0.13 | 1.67s | 51 tps | 99.89% | |
| $1.15 | $2.55 | $0.20 | 1.70s | 48 tps | 99.87% | |
 SiliconFlowfp8 | $1.50 | $3.13 | $0.14 | 1.55s | 40 tps | 99.76% |
 Azureeastus2 | $1.91 | $3.83 | $0.16 | 2.49s | 86 tps | 99.71% |
| $1.65 | $3.30 | $0.33 | 2.98s | 25 tps | 99.45% | |
| $0.43 | $0.86 | $0.04 | 2.87s | 30 tps | 99.23% | |
| $1.42 | $2.83 | $0.12 | 1.86s | 47 tps | 98.99% | |
| $0.45 | $3.48 | $0.10 | 1.42s | 22 tps | 97.53% | |
| $0.96 | $1.91 | $0.08 | 3.20s | 30 tps | 96.82% | |
| $1.05 | $11 | $0.21 | 4.58s | 28 tps | 96.6% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves DeepSeek V4 Pro 0423 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what DeepSeek V4 Pro 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 Pro 0423, by tokens this week.
Activity
3518.2B tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.
