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
16 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.90 | $1.50 | $0.25 | 0.89s | 80 tps | 100% | |
| $1.60 | $3.20 | $0.14 | 1.87s | 57 tps | 100% | |
 SiliconFlowfp8 | $1.50 | $3.13 | $0.14 | 1.64s | 34 tps | 100% |
| $1.69 | $3.38 | $0.14 | 1.09s | 46 tps | 100% | |
 DigitalOcean | $1.04 | $2.09 | $0.21 | 1.17s | 37 tps | 100% |
 DeepInfraus · fp8 | $1.30 | $2.60 | $0.10 | 0.96s | 54 tps | 100% |
| $1.56 | $3.12 | $0.13 | 1.86s | 54 tps | 99.8% | |
| $1.15 | $2.55 | $0.20 | 2.04s | 37 tps | 99.8% | |
| $0.96 | $1.91 | $0.08 | 1.34s | 40 tps | 99.8% | |
| $1.65 | $3.30 | $0.33 | 1.28s | 51 tps | 99.77% | |
| $1.68 | $3.38 | $0.13 | 1.80s | 37 tps | 99.13% | |
| $1.05 | $2.10 | $0.21 | 0.94s | 39 tps | 99.02% | |
| $0.96 | $1.91 | $0.08 | 3.25s | 24 tps | 98.04% | |
| $1.42 | $2.83 | $0.12 | 1.85s | 36 tps | 94.98% | |
 Azureeastus2 | $1.91 | $3.83 | $0.16 | 1.76s | 85 tps | 91.19% |
| $0.45 | $3.48 | $0.10 | 1.51s | 32 tps | 87.85% |
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
3090.0B tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.
