DeepSeek V4 Flash 0731
by DeepSeek · deepseek/deepseek-v4-flash-0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
- Input / 1M tokens
- $0.119
- Output / 1M tokens
- $0.238
- Context
- 1.05M
Specs
| Input price | $0.119 / 1M tokens |
|---|---|
| Output price | $0.238 / 1M tokens |
| Cached input | $0.0238 / 1M tokens |
| Context window | 1.05M tokens |
| Max output | 944K tokens |
| Reads | text |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Jul 31, 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Relace | fp4 | 1.05M | 944K | $0.0398 | $0.152 | $0.028 | 100% | 654 ms | 57 tok/s | Normal | |
| DeepInfra | fp8 | 1.05M | 384K | $0.06 | $0.18 | $0.015 | 100% | 872 ms | 32 tok/s | Normal | |
| Wafer | nvfp4 | 1.05M | 944K | $0.0388 | $0.30 | $0.0378 | 100% | 331 ms | 129 tok/s | Normal | |
| StreamLake | fp8 | 1.02M | 384K | $0.088 | $0.264 | $0.0028 | 100% | 2.17 s | 36 tok/s | Normal | |
| DigitalOcean | — | 1.05M | 944K | $0.119 | $0.238 | $0.0238 | 100% | 671 ms | 136 tok/s | Normal | |
| Wafer | nvfp4 | 1.05M | 944K | $0.14 | $0.23 | $0.135 | 100% | 444 ms | 138 tok/s | Normal | |
| Reka | — | 262K | 131K | $0.10 | $0.28 | $0.04 | 100% | 725 ms | 89 tok/s | Normal | |
| BaseTen | fp8 | 1.05M | 384K | $0.13 | $0.26 | $0.028 | 100% | 364 ms | 102 tok/s | Normal | |
| BaseTen | fp32 | 1.05M | 384K | $0.13 | $0.26 | $0.028 | 100% | 345 ms | 81 tok/s | Normal | |
| Venice | — | 1M | 32.8K | $0.13 | $0.26 | $0.028 | 100% | 575 ms | 97 tok/s | Normal | |
| CoreWeave | fp8 | 262K | 236K | $0.13 | $0.28 | $0.07 | 100% | 429 ms | 133 tok/s | Normal | |
| Cohere | — | 1.05M | 384K | $0.14 | $0.28 | $0.07 | 100% | 410 ms | 164 tok/s | Normal | |
| Parasail | fp8 | 1.05M | 944K | $0.14 | $0.28 | $0.05 | 100% | 643 ms | 94 tok/s | Normal | |
| Sail Research | fp4 | 1.05M | 944K | $0.15 | $0.30 | $0.042 | 100% | 652 ms | 44 tok/s | Normal | |
| Sail Research | fp4 | 1.05M | 944K | $0.15 | $0.30 | $0.042 | 100% | 831 ms | 48 tok/s | Normal | |
| Inceptron | fp4 | 1.05M | 944K | $0.13 | $0.495 | $0.027 | 100% | 820 ms | 50 tok/s | Normal | |
| Alibaba | — | 1M | 393K | $0.176 | $0.528 | $0.0176 | 100% | 2.38 s | 73 tok/s | Normal | |
| Alibaba | — | 1M | 393K | $0.187 | $0.561 | $0.0187 | 100% | 2.21 s | 100 tok/s | Normal | |
| Mancer 2 | fp8 | 1.05M | 944K | $0.20 | $0.60 | — | 100% | 1.09 s | 37 tok/s | Normal | |
| SiliconFlow | fp8 | 1.05M | 393K | $0.22 | $0.66 | $0.028 | 100% | 1.56 s | 21 tok/s | Normal | |
| GMICloud | fp8 | 1.05M | 944K | $0.286 | $0.858 | $0.0091 | 100% | 2.04 s | 58 tok/s | Normal | |
| Phala | — | 1.05M | 393K | $0.308 | $0.924 | $0.0196 | 100% | 2.67 s | 58 tok/s | Normal | |
| Novita | fp8 | 1.05M | 393K | $0.409 | $1.23 | $0.026 | 100% | 1.08 s | 59 tok/s | Normal | |
| AtlasCloud | fp4 | 1.05M | 393K | $0.44 | $1.32 | $0.028 | 100% | 2.06 s | 65 tok/s | Normal | |
| Baidu | fp8 | 1.05M | 131K | $0.44 | $1.32 | $0.014 | 100% | 1.25 s | 70 tok/s | Normal | |
| Cloudflare | — | 1.05M | 944K | $0.44 | $1.32 | $0.014 | 100% | 954 ms | 64 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
#13
by tokens, Oct 29, 2026
510B
tokens that day · 7 days −5%
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 0423
- Input
- $0.091
- Output
- $0.182
- Context
- 1.05M
- DeepSeek
DeepSeek V4 Pro 0813
- Input
- $0.66
- Output
- $1.98
- 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