DeepSeek V4.1 Flash deepseek-v4.1-flash
deepseek-ai · deepseek
unranked — no quality signals yet
- params
- 763.2B
- arch
- moe
- context
- 1024k
- license
- mit open weights
- released
- Sep 2026
- downloads/30d
- 2.1M
# architecture
- layers
- 40
- d_model
- 5120
- heads
- 64q / 1kv
- head dim
- 512
- experts
- top-6 of 384 + 1 shared
- vocab
- 129280
- family
- deepseek_v41_text
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
# benchmarks
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M cache | price src | tps | uptime | ✓ |
|---|---|---|---|---|---|---|---|---|---|
| Featherless | — | — | — | — | via hfrouter | — | — | ||
| Morph | fp8 | 1024k | $0.05 | $0.19 | $0.01 | via openrouter | — | 100.0% | |
| Sail Research | fp4 | 1024k | $0.09 | $0.25 | $0.01 | via openrouter | — | — | |
| Sail Research | fp4 | 1024k | $0.09 | $0.25 | $0.01 | via openrouter | — | — | |
| Sail | 1024k | $0.09 | $0.30 | — | via litellm | — | — | ||
| OpenInference | fp4 | 1024k | $0.04 | $0.50 | $0.01 | via openrouter | — | 99.7% | |
| Relace | fp4 | 1024k | $0.04 | $0.50 | $0.01 | via openrouter | — | 100.0% | |
| Wafer | mxfp4 | 1024k | $0.04 | $0.50 | $0.01 | via openrouter | — | 100.0% | |
| Clf Ai Gateway | 1024k | $0.12 | $0.48 | — | via litellm | — | — | ||
| InferenceNet | fp8 | 1040k | $0.10 | $0.60 | $0.01 | via openrouter | — | 100.0% | |
| InferenceNet | fp8 | 1040k | $0.10 | $0.60 | $0.01 | via openrouter | — | 100.0% | |
| StreamLake | fp8 | 1000k | $0.15 | $0.59 | $0.00 | via openrouter | — | 100.0% | |
| CoreWeave | fp8 | 1024k | $0.13 | $0.65 | $0.00 | via openrouter | — | 100.0% | |
| Scx | 1000k | $0.15 | $0.60 | — | via litellm | — | — | ||
| Vultr | 1024k | $0.15 | $0.60 | — | via modelsdev | — | — | ||
| Prism | 1000k | $0.17 | $0.63 | — | via litellm | — | — | ||
| Alibaba | unknown | 1000k | $0.17 | $0.66 | $0.02 | via openrouter | — | 100.0% | |
| Reka | unknown | 1024k | $0.10 | $0.84 | $0.01 | via openrouter | — | 100.0% | |
| DeepInfra | fp8 | 1024k | $0.20 | $0.60 | — | deepinfra | — | 100.0% | ✓ |
| DeepInfra | fp8 | 1024k | $0.20 | $0.60 | — | deepinfra | — | 100.0% | ✓ |
| DeepInfra | fp8 | 1024k | $0.20 | $0.60 | — | deepinfra | — | 100.0% | ✓ |
| Wafer | mxfp4 | 1024k | $0.19 | $0.65 | $0.01 | via openrouter | — | 100.0% | |
| Coralbricks | 1024k | $0.01 | $1.20 | — | via litellm | — | — | ||
| Wandb | 1049k | $0.20 | $0.65 | — | via litellm | — | — | ||
| GMICloud | fp8 | 1048k | $0.18 | $0.72 | $0.00 | via openrouter | — | 97.8% | |
| Fireworks | unknown | 1024k | $0.21 | $0.84 | $0.00 | via openrouter | — | 100.0% | |
| Aiand | 1024k | $0.30 | $0.60 | — | via litellm | — | — | ||
| DigitalOcean | unknown | 1024k | $0.23 | $0.90 | $0.01 | via openrouter | — | 100.0% | |
| Mancer 2 | fp8 | 1024k | $0.20 | $1.00 | — | via openrouter | — | 98.4% | |
| Kyma | 1024k | $0.27 | $0.81 | — | via litellm | — | — | ||
| Makora | fp8 | 1024k | $0.26 | $1.17 | $0.01 | via openrouter | — | 99.1% | |
| Crusoe | fp8 | 1024k | $0.29 | $1.20 | $0.01 | via openrouter | — | 100.0% | |
| AtlasCloud | fp8 | 1024k | $0.30 | $1.20 | — | atlascloud | — | 100.0% | ✓ |
| Azure | 1000k | $0.30 | $1.20 | $0.01 | via modelsdev | — | — | ||
| Baidu | fp8 | 1024k | $0.30 | $1.20 | $0.01 | via openrouter | — | 100.0% | |
| BaseTen | unknown | 1024k | $0.30 | $1.20 | $0.01 | via openrouter | — | 99.8% | |
| BaseTen | unknown | 1024k | $0.30 | $1.20 | $0.01 | via openrouter | — | 99.9% | |
| Cohere | unknown | 1024k | $0.30 | $1.20 | $0.00 | via openrouter | — | 100.0% | |
| DeepSeek | 1000k | $0.30 | $1.20 | $0.01 | via requesty | — | — | ||
| Fireworks | unknown | 1024k | $0.30 | $1.20 | $0.01 | via openrouter | — | 97.9% | |
| unknown | 1024k | $0.30 | $1.20 | $0.03 | via openrouter | — | 100.0% | ||
| Modal | unknown | 1024k | $0.30 | $1.20 | $0.03 | via openrouter | — | 100.0% | |
| Nebius | fp8 | 1024k | $0.30 | $1.20 | $0.01 | openrouter | — | 97.9% | ✓ |
| Novita | fp8 | 1024k | $0.30 | $1.20 | — | novita | — | 100.0% | ✓ |
| Opencode Go | 1000k | $0.30 | $1.20 | — | via litellm | — | — | ||
| Parasail | fp8 | 1024k | $0.30 | $1.20 | $0.01 | via openrouter | — | 100.0% | |
| Phala | unknown | 1024k | $0.30 | $1.20 | — | phala | — | 97.7% | ✓ |
| PrimeIntellect | unknown | 1024k | $0.30 | $1.20 | $0.01 | via openrouter | — | 100.0% | |
| SiliconFlow | fp8 | 1024k | $0.30 | $1.20 | $0.01 | openrouter | — | 99.9% | ✓ |
| Tencent | 1000k | $0.30 | $1.20 | — | via litellm | — | — | ||
| Together | unknown | 1024k | $0.30 | $1.20 | $0.01 | via openrouter | — | 100.0% | |
| Venice | fp8 | 1000k | $0.30 | $1.20 | — | venice | — | 99.8% | ✓ |
| Zerogpu | 1024k | $0.30 | $1.20 | — | via litellm | — | — | ||
| Inferenceapis | 1024k | $0.40 | $1.60 | — | via litellm | — | — | ||
| Fireworks | unknown | 1024k | $0.45 | $1.80 | $0.01 | via openrouter | — | 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
- llmstats
deepseek-v4.1-flash- openrouter
deepseek/deepseek-v4.1-flash