DeepSeek V4 Flash 0731 deepseek-v4-flash-0731
deepseek-ai · deepseek reasoning efficient
unranked — no quality signals yet
- params
- 158B
- arch
- moe
- context
- 1024k
- license
- mit open weights
- released
- Jul 2026
- reasoning
- yes
- downloads/30d
- 3.2M
# architecture
- layers
- 43
- d_model
- 4096
- heads
- 64q / 1kv
- head dim
- 512
- experts
- top-6 of 256 + 1 shared
- vocab
- 129280
- family
- deepseek_v4
signal path of one layer, generated from the registry's structured fields — dimension lines quote the model's real numbers; an MoE trace forks at the router, a dense trace runs straight through. Geometry fields come from the repo's config.json.
# trend
methodology changed during this history window; score movement across that boundary is not model movement. See methodology v6.
# benchmarks
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M cache | price src | tps | uptime | ✓ |
|---|---|---|---|---|---|---|---|---|---|
| Featherless | — | — | — | — | via hfrouter | — | — | ||
| Nebius | — | — | — | — | nebius | — | — | ✓ | |
| Scaleway | — | — | — | — | via hfrouter | 145 | — | ||
| Relace | fp4 | 1024k | $0.07 | $0.14 | $0.01 | via openrouter | — | 100.0% | |
| DeepInfra | fp8 | 1024k | $0.06 | $0.18 | — | deepinfra | — | 100.0% | ✓ |
| Sail | 1024k | $0.09 | $0.18 | — | via litellm | — | — | ||
| Wafer | nvfp4 | 1024k | $0.06 | $0.30 | $0.04 | via openrouter | — | 100.0% | |
| StreamLake | fp8 | 1000k | $0.09 | $0.26 | $0.00 | via openrouter | — | 100.0% | |
| Vultr | 1024k | $0.10 | $0.25 | — | via modelsdev | — | — | ||
| Reka | unknown | 256k | $0.10 | $0.28 | $0.04 | via openrouter | — | 99.9% | |
| DigitalOcean | unknown | 1024k | $0.12 | $0.24 | $0.02 | via openrouter | — | 100.0% | |
| BaseTen | fp8 | 1024k | $0.13 | $0.26 | $0.03 | via openrouter | — | 100.0% | |
| BaseTen | fp32 | 1024k | $0.13 | $0.26 | $0.03 | via openrouter | — | 100.0% | |
| Venice | unknown | 1000k | $0.13 | $0.26 | — | venice | — | 99.7% | ✓ |
| Wafer | nvfp4 | 1024k | $0.14 | $0.23 | $0.14 | via openrouter | — | 100.0% | |
| CoreWeave | fp8 | 256k | $0.13 | $0.28 | $0.07 | via openrouter | — | 100.0% | |
| Wandb | 262k | $0.13 | $0.28 | — | via litellm | — | — | ||
| Cohere | unknown | 1024k | $0.14 | $0.28 | $0.07 | via openrouter | — | 100.0% | |
| Parasail | fp8 | 1024k | $0.14 | $0.28 | $0.05 | via openrouter | — | 100.0% | |
| Together | 1024k | $0.14 | $0.28 | $0.03 | via modelsdev | — | — | ||
| Sail Research | fp4 | 1024k | $0.15 | $0.30 | $0.04 | via openrouter | — | 100.0% | |
| Sail Research | fp4 | 1024k | $0.15 | $0.30 | $0.04 | via openrouter | — | 100.0% | |
| Inceptron | fp4 | 1024k | $0.13 | $0.49 | $0.03 | via openrouter | — | 100.0% | |
| Inferenceapis | 1024k | $0.19 | $0.38 | — | via litellm | — | — | ||
| Qwen Ai Platform | 1000k | $0.20 | $0.40 | — | via litellm | — | — | ||
| Qwencloud | 1000k | $0.20 | $0.40 | — | via litellm | — | — | ||
| Alibaba | unknown | 1000k | $0.18 | $0.53 | $0.02 | via openrouter | — | 99.6% | |
| Alibaba | unknown | 1000k | $0.19 | $0.56 | $0.02 | via openrouter | — | 99.9% | |
| Mancer 2 | fp8 | 1024k | $0.20 | $0.60 | — | via openrouter | — | 100.0% | |
| Fireworks | 1000k | $0.22 | $0.66 | $0.01 | via requesty | — | — | ||
| SiliconFlow | fp8 | 1024k | $0.22 | $0.66 | $0.03 | openrouter | — | 99.8% | ✓ |
| GMICloud | fp8 | 1048k | $0.29 | $0.86 | $0.01 | via openrouter | — | 99.6% | |
| AtlasCloud | fp4 | 1024k | $0.44 | $1.32 | — | atlascloud | — | 100.0% | ✓ |
| Azure | 1000k | $0.44 | $1.32 | — | via litellm | — | — | ||
| Baidu | fp8 | 1024k | $0.44 | $1.32 | $0.01 | via openrouter | — | 100.0% | |
| Chutes | fp8 | 1024k | $0.44 | $1.32 | $0.04 | via openrouter | — | 100.0% | |
| Cloudflare | unknown | 1024k | $0.44 | $1.32 | $0.01 | via openrouter | — | 100.0% | |
| Novita | fp8 | 1024k | $0.44 | $1.32 | — | novita | — | 100.0% | ✓ |
| Phala | unknown | 1024k | $0.44 | $1.32 | — | phala | — | 100.0% | ✓ |
sorted by blended price ((3·input + output) / 4 per 1M) · ✓ = the provider's own catalog confirms the offer · "via …" prices are what the aggregator routing the offer charges, not the provider's own list price
source aliases
- aa
deepseek-v4-flash,deepseek-v4-flash-non-reasoning- hf
bartowski/DeepSeek-V4-Flash-0731-GGUF,unsloth/DeepSeek-V4-Flash-0731- openrouter
deepseek/deepseek-v4-flash-0731