DeepSeek V4 Pro 0813
by DeepSeek · deepseek/deepseek-v4-pro-0813
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
- Input / 1M tokens
- $0.66
- Output / 1M tokens
- $1.98
- Context
- 1.05M
Specs
| Input price | $0.66 / 1M tokens |
|---|---|
| Output price | $1.98 / 1M tokens |
| Cached input | $0.022 / 1M tokens |
| Context window | 1.05M tokens |
| Max output | 393K tokens |
| Reads | text |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Aug 12, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
26 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Sail Research | fp4 | 1.05M | 384K | $0.675 | $1.20 | $0.0975 | 100% | 913 ms | 83 tok/s | Normal | |
| Sail Research | fp4 | 1.05M | 384K | $0.675 | $1.20 | $0.0975 | 100% | 811 ms | 87 tok/s | Normal | |
| Alibaba | — | 1M | 393K | $0.581 | $1.74 | $0.0581 | 100% | 1.60 s | 61 tok/s | Normal | |
| Alibaba | — | 1M | 393K | $0.66 | $1.98 | $0.066 | 100% | 1.08 s | 62 tok/s | Normal | |
| DeepSeek | — | 1.05M | 393K | $0.66 | $1.98 | $0.022 | 100% | 1.01 s | 37 tok/s | Normal | |
| StreamLake | — | 1.02M | 384K | $0.66 | $1.98 | $0.022 | 100% | 1.83 s | 46 tok/s | Normal | |
| Ionstream | — | 1.05M | 944K | $0.37 | $2.93 | $0.088 | 100% | 659 ms | 52 tok/s | Normal | |
| Phala | — | 1.05M | 393K | $0.957 | $2.88 | $0.099 | — | 2.27 s | 41 tok/s | Normal | |
| DeepInfra | fp8 | 1.05M | 16.4K | $1.30 | $2.60 | $0.10 | 100% | 1.29 s | 68 tok/s | Normal | |
| Novita | fp8 | 1.05M | 393K | $0.99 | $2.97 | $0.033 | 100% | 2.38 s | 49 tok/s | Normal | |
| Relace | fp4 | 1.05M | 393K | $0.103 | $4.00 | $0.10 | 100% | 1.22 s | 27 tok/s | Normal | |
| GMICloud | fp8 | 1.05M | 944K | $1.06 | $3.17 | $0.0352 | — | 2.25 s | 57 tok/s | Normal | |
| Wafer | mxfp4 | 1.05M | 944K | $0.115 | $4.30 | $0.11 | 100% | 606 ms | 103 tok/s | Normal | |
| Wafer | mxfp4 | 1.05M | 944K | $0.285 | $4.30 | $0.284 | 100% | 505 ms | 107 tok/s | Normal | |
| DekaLLM | — | 1.05M | 944K | $0.88 | $3.80 | $0.15 | 100% | 1.09 s | 95 tok/s | Normal | |
| CoreWeave | fp8 | 1.05M | 944K | $1.31 | $3.96 | $0.044 | 100% | 888 ms | 118 tok/s | Normal | |
| AtlasCloud | fp8 | 1.05M | 393K | $1.32 | $3.96 | $0.132 | 100% | 1.32 s | 60 tok/s | Normal | |
| Baidu | fp8 | 1.05M | 393K | $1.32 | $3.96 | $0.042 | 100% | 1.53 s | 58 tok/s | Normal | |
| BaseTen | fp4 | 1.05M | 262K | $1.32 | $3.96 | $0.132 | — | 624 ms | 52 tok/s | Normal | |
| Cloudflare | — | 1.05M | 944K | $1.32 | $3.96 | $0.044 | 100% | 936 ms | 43 tok/s | Normal | |
| DigitalOcean | — | 1.05M | 944K | $1.32 | $3.96 | $0.044 | 100% | 752 ms | 46 tok/s | Normal | |
| Nebius | fp8 | 1.05M | 944K | $1.32 | $3.96 | $0.04 | 100% | 1.14 s | 118 tok/s | Normal | |
| Parasail | fp8 | 1.05M | 944K | $1.32 | $3.96 | $0.044 | 100% | 1.03 s | 46 tok/s | Normal | |
| SiliconFlow | fp8 | 1.05M | 393K | $1.32 | $3.96 | $0.044 | 100% | 1.96 s | 66 tok/s | Normal | |
| Together | — | 1.05M | 944K | $1.32 | $3.96 | $0.13 | 100% | 703 ms | 117 tok/s | Normal | |
| Venice | — | 1M | 32.8K | $1.65 | $4.95 | $0.165 | — | 1.43 s | 51 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Usage
#32
by tokens, Oct 29, 2026
123B
tokens that day · 7 days −18%
Data as of 2026-10-30T18:12:03.879Z.All rankings
Related models
- DeepSeek
DeepSeek V4.1 Flash 1017
- Input
- $0.15
- Output
- $0.60
- Context
- 1.05M
- DeepSeek
DeepSeek V4.1 Flash
- Input
- $0.045
- Output
- $0.50
- Context
- 1.05M
- DeepSeek
DeepSeek V4 Flash 0731
- Input
- $0.119
- Output
- $0.238
- Context
- 1.05M
- DeepSeek
DeepSeek V4 Flash 0423
- Input
- $0.091
- Output
- $0.182
- Context
- 1.05M
- DeepSeek
DeepSeek V4 Pro 0423
- Input
- $0.948
- Output
- $1.90
- Context
- 1.05M
- DeepSeek
DeepSeek V4.1 Flash (batch)
- Input
- $0.05
- Output
- $0.15
- Context
- 1.05M