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. This is the GA release of DeepSeek V4 Flash.

deepseek/deepseek-v4-flash-0731
Organization
DeepSeek
Providers
54
Context
1,000,000
Output limit
384,000
Knowledge
2025-05
Release
2026-07-31
Updated
2026-07-31
Weights
Open
Input
text
Output
text
Capabilities
Tools, Reasoning, Structured, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

94 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
AIHubMix
deepseek-v4-flash-0731
1,000,000384,000$0.142 / $0.284YesYesYes
View
AIHubMix
deepseek-v4-flash-0731-fast
1,000,000384,000$0.28 / $1.40YesYesYes
View
AKI.IO
deepseek-v4-flash-0731-284b
1,048,57681,920$0.20 / $0.50YesYesYes
View
Alibaba
deepseek-v4-flash-0731
1,000,000384,000$0.20 / $0.40YesYesYes
View
Alibaba Token Plan
deepseek-v4-flash-0731
1,000,000384,000$0.00 / $0.00YesYesYes
View
Alibaba Token Plan (China)
deepseek-v4-flash-0731
1,000,000384,000$0.00 / $0.00YesYesYes
View
Ambient
deepseek/deepseek-v4-flash-0731
1,048,5761,048,576$0.08 / $0.18YesYesYes
View
AMD
DeepSeek-V4-Flash
1,048,576384,000$0.14 / $0.28YesYesYes
View
Arcee
deepseek/deepseek-v4-flash-latest
1,048,576384,000$0.14 / $0.28YesYesYes
View
Baseten
deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000$0.13 / $0.26YesYesYes
View
Bothub
deepseek-v4-flash-0731
1,000,000384,000$0.10 / $0.28YesYesYes
View
Charm Hyper
deepseek-v4-flash-0731
1,000,000384,000$0.44 / $1.32YesYesYes
View
Chutes
deepseek-ai/DeepSeek-V4-Flash-0731-TEE
1,048,576131,072$0.44 / $1.32YesYesYes
View
Cloudflare Workers AI
@cf/deepseek-ai/deepseek-v4-flash-0731
1,048,5761,048,576$0.44 / $1.32YesYesYes
View
CoreWeave
deepseek-ai/DeepSeek-V4-Flash-0731
262,144262,144$0.13 / $0.28YesYesYes
View
Cortecs
deepseek-v4-flash-0731
1,048,5761,048,576$0.09 / $0.17YesYes—
View
CrofAI
deepseek-v4-flash-0731
1,000,000131,072$0.08 / $0.10YesYesYes
View
Deep Infra
deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000$0.06 / $0.18YesYesYes
View
DigitalOcean
deepseek-v4-flash-0731
1,048,5761,048,576$0.14 / $0.28YesYesYes
View
Eden AI
cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731
1,048,576384,000$0.44 / $1.32YesYesYes
View
Eden AI
flexai/DeepSeek-V4-Flash-0731
1,048,576384,000$0.06 / $0.18YesYesYes
View
Eden AI
tensorx/deepseek/deepseek-v4-flash-0731
1,048,576384,000$0.25 / $0.30YesYesNo
View
Eden AI
nebius/deepseek-ai/DeepSeek-V4-Flash-0731
1,024,000384,000$0.14 / $0.28YesYesYes
View
Eden AI
qwen/deepseek-v4-flash-0731
1,000,000384,000$0.22 / $0.66YesYesYes
View
Eden AI
scaleway/deepseek-v4-flash-0731
256,000384,000$0.449 / $0.898YesYesNo
View
Eden AI
together_ai/deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000$0.14 / $0.28YesYesYes
View
Eden AI
databricks/databricks-deepseek-v4-flash-0731
1,000,000384,000$0.14 / $0.28YesYesNo
View
Eden AI
deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000$0.06 / $0.18YesYesYes
View
EmpirioLabs AI
deepseek-v4-flash-0731
1,000,000393,216$0.424 / $1.272YesYesYes
View
engy
deepseek-v4-flash-0731
1,048,576128,000$0.045 / $0.09YesYesYes
View
GreenPT
deepseek-v4-flash-0731
1,000,000384,000$0.1596 / $0.399YesYesYes
View
Hugging Face
deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000$0.14 / $0.28YesYesYes
View
Inceptron
deepseek-ai/DeepSeek-V4-Flash-0731
1,048,5761,048,576$0.13 / $0.28YesYesYes
View
IteraCompute
deepseek/deepseek-v4-flash-0731
970,000393,216$0.34 / $1.05YesYesYes
View
Kilo Gateway
deepseek/deepseek-v4-flash-0731
1,048,576943,718$0.44 / $1.32YesYesYes
View
Melious
deepseek-v4-flash-0731
1,000,000384,000$0.11592 / $0.2898YesYesYes
View
Merge Gateway
deepseek/deepseek-v4-flash-0731
1,048,576384,000$0.035 / $0.07YesYesYes
View
Merge Gateway
deepseek/deepseek-v4-flash-0731-fast
1,000,000384,000$0.28 / $0.56YesNoNo
View
NanoGPT
deepseek/deepseek-v4-flash-0731:thinking
1,000,000131,072$0.05 / $0.16YesYesYes
View
NanoGPT
deepseek/deepseek-v4-flash-0731
1,000,000131,072$0.05 / $0.16YesYesYes
View
Nebius Token Factory
deepseek-ai/DeepSeek-V4-Flash-0731
1,024,0001,024,000$0.14 / $0.28YesYesYes
View
Neuralwatt
deepseek-v4-flash-speed
1,048,560393,216$0.14 / $0.28YesYesYes
View
Nvidia
deepseek-ai/deepseek-v4-flash-0731
1,000,000384,000$0.00 / $0.00YesYesYes
View
Ofox
deepseek/deepseek-v4-flash-0731
1,000,000384,000$0.308 / $0.924YesYesYes
View
Ollama Cloud
deepseek-v4-flash:0731
1,048,5761,048,576$0.22 / $0.66YesYesYes
View
OpenCode Go
deepseek-v4-flash
1,000,000384,000$0.15 / $0.60YesYesYes
View
OpenCode Zen
deepseek-v4-flash-free
200,000128,000$0.00 / $0.00YesYesYes
View
OpenCode Zen
deepseek-v4-flash
1,000,000384,000$0.14 / $0.28YesYesYes
View
OpenReason
deepseek-ai/deepseek-v4-flash-0731
1,000,000384,000$0.1371 / $0.2743YesYesYes
View
Alibabavia OpenRouter
deepseek/deepseek-v4-flash-0731
unknown
1,000,000393,216$0.352 / $1.056YesYesYes
View
AtlasCloudvia OpenRouter
deepseek/deepseek-v4-flash-0731
fp4
1,048,576393,216$0.44 / $1.32YesYesYes
View
Baiduvia OpenRouter
deepseek/deepseek-v4-flash-0731
fp8
1,048,576131,072$0.44 / $1.32YesYesYes
View
BaseTenvia OpenRouter
deepseek/deepseek-v4-flash-0731
fp8
1,048,576384,000$0.13 / $0.26YesYesNo
View
Cloudflarevia OpenRouter
deepseek/deepseek-v4-flash-0731
unknown
1,048,576943,718$0.44 / $1.32YesYesYes
View
Coherevia OpenRouter
deepseek/deepseek-v4-flash-0731
unknown
1,048,576384,000$0.14 / $0.28YesYesYes
View
CoreWeavevia OpenRouter
deepseek/deepseek-v4-flash-0731
fp8
262,144235,929$0.13 / $0.28YesYesNo
View
DeepInfravia OpenRouter
deepseek/deepseek-v4-flash-0731
fp8
1,048,576384,000$0.06 / $0.18YesYesYes
View
DigitalOceanvia OpenRouter
deepseek/deepseek-v4-flash-0731
unknown
1,048,576943,718$0.119 / $0.238YesYesYes
View
GMICloudvia OpenRouter
deepseek/deepseek-v4-flash-0731
fp8
1,048,575943,717$0.286 / $0.858YesYesNo
View
Inceptronvia OpenRouter
deepseek/deepseek-v4-flash-0731
fp4
1,048,576943,718$0.05 / $0.65YesYesYes
View
Mancer 2via OpenRouter
deepseek/deepseek-v4-flash-0731
fp8
1,048,576943,718$0.20 / $0.60YesYesYes
View
Morphvia OpenRouter
deepseek/deepseek-v4-flash-0731
bf16
1,048,576943,718$0.142 / $0.40YesYesYes
View
NextBitvia OpenRouter
deepseek/deepseek-v4-flash-0731
fp8
1,048,576943,718$0.352 / $1.056YesYesYes
View
Novitavia OpenRouter
deepseek/deepseek-v4-flash-0731
fp8
1,048,576393,216$0.4092 / $1.2276YesYesNo
View
OpenInferencevia OpenRouter
deepseek/deepseek-v4-flash-0731
fp4
1,048,576943,718$0.01976 / $1.664YesYesYes
View
Parasailvia OpenRouter
deepseek/deepseek-v4-flash-0731
fp8
1,048,576943,718$0.14 / $0.28YesYesYes
View
Phalavia OpenRouter
deepseek/deepseek-v4-flash-0731
unknown
1,048,576393,216$0.308 / $0.924YesYesYes
View
Rekavia OpenRouter
deepseek/deepseek-v4-flash-0731
unknown
262,144131,072$0.021 / $0.528YesYesYes
View
Relacevia OpenRouter
deepseek/deepseek-v4-flash-0731
fp4
1,048,576943,718$0.0152 / $1.28YesYesNo
View
Sail Researchvia OpenRouter
deepseek/deepseek-v4-flash-0731
fp4
1,048,576943,718$0.019 / $0.42YesYesYes
View
Sail Researchvia OpenRouter
deepseek/deepseek-v4-flash-0731
fp4
1,048,576943,718$0.019 / $0.30YesYesYes
View
SiliconFlowvia OpenRouter
deepseek/deepseek-v4-flash-0731
fp8
1,048,576393,216$0.22 / $0.66YesYesYes
View
StreamLakevia OpenRouter
deepseek/deepseek-v4-flash-0731
fp8
1,024,000384,000$0.044 / $0.132YesYesNo
View
Togethervia OpenRouter
deepseek/deepseek-v4-flash-0731
unknown
1,048,576943,718$0.14 / $0.28YesYesYes
View
Venicevia OpenRouter
deepseek/deepseek-v4-flash-0731
unknown
1,000,00032,768$0.175 / $0.35YesYesYes
View
Wafervia OpenRouter
deepseek/deepseek-v4-flash-0731
unknown
1,048,576943,718$0.12 / $0.84YesYesYes
View
OrcaRouter
deepseek/deepseek-v4-flash-0731
1,000,000384,000$0.147 / $0.295YesYesYes
View
Perplexity Agent
deepseek/deepseek-v4-flash-0731
1,000,000384,000$0.13 / $0.26YesYesYes
View
Requesty
deepseek-v4-flash-0731
1,048,576131,072$0.28 / $0.56YesYesYes
View
Requesty
deepseek-v4-flash-0731@eu
1,048,576131,072$0.28 / $0.56YesYesYes
View
RunInfra
deepseek-ai/DeepSeek-V4-Flash-0731
1,048,57632,768$0.13 / $0.27YesYesYes
View
Scaleway
deepseek-v4-flash-0731
256,00032,768$0.468 / $0.936YesYesYes
View
SCNet Token Plan
DeepSeek-V4-Flash-0731
1,000,000384,000$0.00 / $0.00YesYesYes
View
SiliconFlow
deepseek-ai/DeepSeek-V4-Flash-0731
1,000,000384,000$0.22 / $0.66YesYesYes
View
TensorX
deepseek/deepseek-v4-flash-0731
1,048,576384,000$0.25 / $0.30YesYesYes
View
Together AI
deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000$0.14 / $0.28YesYesYes
View
Umans AI
umans-deepseek-v4-flash-0731
1,048,576393,215$0.14 / $0.28YesYesYes
View
Umans AI Coding Plan
umans-deepseek-v4-flash-0731
1,048,576393,215$0.00 / $0.00YesYesYes
View
Venice AI
deepseek-v4-flash-0731
1,000,00032,768$0.175 / $0.35YesYesYes
View
Venice AI
deepseek-v4-flash-0731-fast
1,000,00032,768$0.35 / $0.70YesYesYes
View
Vercel AI Gateway
deepseek/deepseek-v4-flash-0731
1,000,000384,000$0.076 / $0.153YesYesYes
View
Vivgrid
deepseek-v4-flash
1,000,000384,000$0.15 / $0.30YesYesYes
View
Volcengine Ark
deepseek-v4-flash-ga-260731
1,000,000384,000$0.4453 / $1.3359YesYesYes
View
Vultr
deepseek-v4-flash-0731
1,048,576384,000$0.10 / $0.25YesYesYes
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$0.00Per 1M input tokens
Output from$0.00Per 1M output tokens
Available offers94Across 54 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 10 lowest-priced configurations
InputOutput
Relacerelace/fp4
$0.0152$1.28
Sail Researchsail-research/us
$0.019$0.42
Sail Researchsail-research/fp4
$0.019$0.30
OpenInferenceopen-inference/fp4
$0.01976$1.664
Rekareka
$0.021$0.528
StreamLakestreamlake/fp8
$0.044$0.132
Inceptroninceptron/fp4
$0.05$0.65
DeepInfradeepinfra/fp8
$0.06$0.18
DigitalOceandigitalocean
$0.119$0.238
Waferwafer/fast
$0.12$0.84
deepseek/deepseek-v4-flash-0731Observed
Input
$0.0152
Output
$1.28
Cache read
$0.0152
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Alibabaalibaba$0.352$1.056$0.0352—
AtlasCloudatlas-cloud/fp4$0.44$1.32$0.028—
Baidubaidu/fp8$0.44$1.32$0.014—
BaseTenbaseten/fp8$0.13$0.26$0.028—
Cloudflarecloudflare$0.44$1.32$0.014—
Coherecohere$0.14$0.28$0.07—
CoreWeavecoreweave/fp8$0.13$0.28$0.07—
DeepInfradeepinfra/fp8$0.06$0.18$0.015—
DigitalOceandigitalocean$0.119$0.238$0.0238—
GMICloudgmicloud/fp8$0.286$0.858$0.0091—
Inceptroninceptron/fp4$0.05$0.65$0.027—
Mancer 2mancer/fp8$0.20$0.60——
Morphmorph/bf16$0.142$0.40$0.036—
NextBitnextbit/fp8$0.352$1.056$0.012—
Novitanovita/fp8$0.4092$1.2276$0.02604—
OpenInferenceopen-inference/fp4$0.01976$1.664$0.01976—
Parasailparasail/fp8$0.14$0.28$0.05—
Phalaphala$0.308$0.924$0.0196—
Rekareka$0.021$0.528$0.0056—
Relacerelace/fp4$0.0152$1.28$0.0152—
Sail Researchsail-research/us$0.019$0.42$0.012—
Sail Researchsail-research/fp4$0.019$0.30$0.014—
SiliconFlowsiliconflow/fp8$0.22$0.66$0.028—
StreamLakestreamlake/fp8$0.044$0.132$0.0014—
Togethertogether$0.14$0.28$0.03—
Venicevenice$0.175$0.35$0.035—
Waferwafer/fast$0.12$0.84$0.05—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Alibabaalibaba
1,544–6,948.75 ms
AtlasCloudatlas-cloud/fp4
2,543.5–4,745.59 ms
Baidubaidu/fp8
669–3,609.09 ms
Cloudflarecloudflare
1,163–4,937.2 ms
Coherecohere
378–4,218.15 ms
CoreWeavecoreweave/fp8
500–6,701.08 ms
All latency percentiles 26 endpoints
EndpointP50P75P90P99
Alibabaalibaba1,544 ms2,081.75 ms2,885.3 ms6,948.75 ms
AtlasCloudatlas-cloud/fp42,543.5 ms3,321 ms3,873.4 ms4,745.59 ms
Baidubaidu/fp8669 ms874.25 ms1,261 ms3,609.09 ms
Cloudflarecloudflare1,163 ms1,605 ms2,319 ms4,937.2 ms
Coherecohere378 ms721 ms976.9 ms4,218.15 ms
CoreWeavecoreweave/fp8500 ms1,234.25 ms1,763 ms6,701.08 ms
DeepInfradeepinfra/fp8714 ms1,301.25 ms2,156 ms7,507.09 ms
DigitalOceandigitalocean512 ms685 ms1,015.9 ms2,728.7 ms
GMICloudgmicloud/fp81,703 ms1,959 ms2,343 ms4,004.78 ms
Inceptroninceptron/fp4513.5 ms798 ms1,342.2 ms5,387.83 ms
Mancer 2mancer/fp8918.5 ms1,269.75 ms1,845.1 ms5,396.49 ms
Morphmorph/bf16673 ms924 ms1,478.6 ms4,302.56 ms
NextBitnextbit/fp82,449 ms3,293.25 ms3,931.5 ms5,987.55 ms
Novitanovita/fp81,829 ms2,350.5 ms2,821.8 ms8,052.2 ms
OpenInferenceopen-inference/fp41,125 ms2,599 ms5,821 ms7,900.72 ms
Parasailparasail/fp8741 ms3,593 ms10,713 ms58,778.54 ms
Phalaphala1,800 ms2,146 ms2,489.4 ms5,065.78 ms
Rekareka599 ms921.25 ms1,620 ms5,548.09 ms
Relacerelace/fp41,034 ms1,887.25 ms3,161.7 ms12,741.65 ms
Sail Researchsail-research/us1,723.5 ms2,508 ms3,635.9 ms7,609.8 ms
Sail Researchsail-research/fp41,997 ms3,054 ms4,451.9 ms16,202.22 ms
SiliconFlowsiliconflow/fp81,388 ms1,931 ms3,570.2 ms12,619.36 ms
StreamLakestreamlake/fp81,277 ms1,820 ms2,926.9 ms9,069.07 ms
Togethertogether669 ms1,169 ms2,876.2 ms25,340.76 ms
Venicevenice906 ms1,428 ms2,306 ms31,047.7 ms
Waferwafer/fast461 ms601 ms916 ms2,128.36 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Alibabaalibaba
85–162.86 t/s
AtlasCloudatlas-cloud/fp4
75–217.74 t/s
Baidubaidu/fp8
104–283 t/s
Cloudflarecloudflare
55–74 t/s
Coherecohere
162–472 t/s
CoreWeavecoreweave/fp8
120–220 t/s
All throughput percentiles 26 endpoints
EndpointP50P75P90P99
Alibabaalibaba85 t/s116 t/s134 t/s162.86 t/s
AtlasCloudatlas-cloud/fp475 t/s117.5 t/s155.4 t/s217.74 t/s
Baidubaidu/fp8104 t/s146 t/s188 t/s283 t/s
Cloudflarecloudflare55 t/s62 t/s67 t/s74 t/s
Coherecohere162 t/s232 t/s331 t/s472 t/s
CoreWeavecoreweave/fp8120 t/s143 t/s167 t/s220 t/s
DeepInfradeepinfra/fp856 t/s74 t/s94 t/s141.09 t/s
DigitalOceandigitalocean45 t/s48 t/s51 t/s58 t/s
GMICloudgmicloud/fp867 t/s79 t/s94 t/s150 t/s
Inceptroninceptron/fp479 t/s112 t/s161 t/s262 t/s
Mancer 2mancer/fp888 t/s111 t/s137.2 t/s176 t/s
Morphmorph/bf1644 t/s56 t/s68 t/s133.04 t/s
NextBitnextbit/fp866 t/s84.75 t/s97 t/s125.64 t/s
Novitanovita/fp871 t/s82 t/s90 t/s124 t/s
OpenInferenceopen-inference/fp434 t/s38 t/s40 t/s42 t/s
Parasailparasail/fp8101 t/s134 t/s168 t/s264 t/s
Phalaphala62 t/s83 t/s105.8 t/s163.19 t/s
Rekareka98 t/s140 t/s193 t/s302 t/s
Relacerelace/fp427 t/s43 t/s82 t/s186.09 t/s
Sail Researchsail-research/us33 t/s40 t/s46 t/s59 t/s
Sail Researchsail-research/fp432 t/s39 t/s46 t/s61 t/s
SiliconFlowsiliconflow/fp856 t/s77 t/s94 t/s131.47 t/s
StreamLakestreamlake/fp840 t/s54 t/s71 t/s116 t/s
Togethertogether48 t/s71 t/s95 t/s150 t/s
Venicevenice70 t/s93 t/s123 t/s165 t/s
Waferwafer/fast97 t/s107 t/s118 t/s154 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 27 endpoints
Endpoint5 minutes30 minutes24 hours
Alibabaalibaba
AtlasCloudatlas-cloud/fp4
Baidubaidu/fp8
BaseTenbaseten/fp8
Cloudflarecloudflare
Coherecohere
CoreWeavecoreweave/fp8
DeepInfradeepinfra/fp8
DigitalOceandigitalocean
GMICloudgmicloud/fp8
Inceptroninceptron/fp4
Mancer 2mancer/fp8
Morphmorph/bf16
NextBitnextbit/fp8
Novitanovita/fp8
OpenInferenceopen-inference/fp4
Parasailparasail/fp8
Phalaphala
Rekareka
Relacerelace/fp4
Sail Researchsail-research/us
Sail Researchsail-research/fp4
SiliconFlowsiliconflow/fp8
StreamLakestreamlake/fp8
Togethertogether
Venicevenice
Waferwafer/fast

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations
deepseek/deepseek-v4-flash-0731Observed
Benchmark profileArtificial Analysis · shared source scale from 0 to 70
Coding69.1
Agentic41
Intelligence34.3
Design ArenaCategoryEloWin rateRank
models3d1,22448.6%38
modelsasciiart1,10033.3%61
modelscodecategories1,23646.4%42
modelsdataviz1,19041.1%57
modelsgamedev1,22144.6%43
modelssvg1,18645.1%30
modelsuicomponent1,24246.8%41
modelswebsite1,24546.7%40

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
search browsecompDeepseek V4 Flash 0731
77%
search widesearchDeepseek V4 Flash 0731
77.129%
search dsqaDeepseek V4 Flash 0731
81.655%
tau bench verified airlineDeepSeek: DeepSeek V4 Flash 0731
73.407%
gpqa diamondDeepSeek: DeepSeek V4 Flash 0731
86.251%
EvaluationConfigurationSourceResultsDetails
search browsecompDeepseek V4 Flash 0731deepseek/deepseek-v4-flash-0731OpenRouter77%
Details
search widesearchDeepseek V4 Flash 0731deepseek/deepseek-v4-flash-0731OpenRouter77.129%
Details
search dsqaDeepseek V4 Flash 0731deepseek/deepseek-v4-flash-0731OpenRouter81.655%
Details
tau bench verified airlineDeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-20260731OpenRouter73.407%
Details
models · uicomponentDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,242 Elo
Details
models · asciiartDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,100 Elo
Details
models · websiteDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,245 Elo
Details
models · gamedevDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,221 Elo
Details
models · 3dDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,224 Elo
Details
models · codecategoriesDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,236 Elo
Details
models · svgDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,186 Elo
Details
Composite indicesDeepSeek V4 Flash 0731 (Reasoning, Max Effort)deepseek/deepseek-v4-flash-20260731Artificial AnalysisIntelligence 34.3 · Coding 69.1 · Agentic 41
Details
models · datavizDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,190 Elo
Details
gpqa diamondDeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-20260731OpenRouter86.251%
Details

Showing 11 of 14 records in this dataset.

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Codexdeepseek/deepseek-v4-flash-202607311 turn
$0.000376
Details
Hermes Agentdeepseek/deepseek-v4-flash-202607312–9 turns
$0.003236
Details
Hermes Agentdeepseek/deepseek-v4-flash-2026073110–49 turns
$0.025838
Details
Kilo Codedeepseek/deepseek-v4-flash-202607311 turn
$0.000327
Details
Hermes Agentdeepseek/deepseek-v4-flash-2026073150+ turns
$0.190303
Details
Kilo Codedeepseek/deepseek-v4-flash-202607312–9 turns
$0.005178
Details
Codexdeepseek/deepseek-v4-flash-2026073110–49 turns
$0.01441
Details
Codexdeepseek/deepseek-v4-flash-202607312–9 turns
$0.00208
Details
Claude Codedeepseek/deepseek-v4-flash-202607311 turn
$0.001331
Details
Claude Codedeepseek/deepseek-v4-flash-202607312–9 turns
$0.004979
Details
Claude Codedeepseek/deepseek-v4-flash-2026073110–49 turns
$0.033062
Details
Kilo Codedeepseek/deepseek-v4-flash-2026073110–49 turns
$0.030639
Details
Hermes Agentdeepseek/deepseek-v4-flash-202607311 turn
$0.000569
Details
Claude Codedeepseek/deepseek-v4-flash-2026073150+ turns
$0.238889
Details
Kilo Codedeepseek/deepseek-v4-flash-2026073150+ turns
$0.264569
Details
Codexdeepseek/deepseek-v4-flash-2026073150+ turns
$0.019858
Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days
Daily token usage91,634,195,673,962 reported tokens · 65 days with observations
Jul 6, 2026Oct 3, 2026
Daily observations · 65 days
Date (UTC)Reported tokensReported routes
Oct 3, 2026708,736,901,4751
Oct 2, 2026748,543,750,0001
Oct 1, 2026922,138,361,5031
Sep 30, 2026968,247,430,3811
Sep 29, 2026945,806,096,4521
Sep 28, 2026948,299,816,0311
Sep 27, 2026841,010,990,3671
Sep 26, 20261,085,804,508,4421
Sep 25, 20261,114,855,555,3731
Sep 24, 20261,138,661,880,7041
Sep 23, 20261,200,912,439,3161
Sep 22, 20261,236,716,483,4991
Sep 21, 20261,206,123,550,6631
Sep 20, 20261,115,867,963,5551
Sep 19, 20261,213,436,800,9011
Sep 18, 20261,190,061,791,4851
Sep 17, 20261,327,505,194,1941
Sep 16, 20261,349,217,150,9521
Sep 15, 20261,506,862,691,0281
Sep 14, 20261,737,561,958,1491
Sep 13, 20261,441,764,456,8901
Sep 12, 20261,344,100,323,5271
Sep 11, 20261,909,849,336,2221
Sep 10, 20261,949,990,851,9161
Sep 9, 20261,618,860,272,5761
Sep 8, 20261,721,613,635,9881
Sep 7, 20261,576,698,141,6261
Sep 6, 20261,520,532,796,3351
Sep 5, 20261,732,594,234,2861
Sep 4, 20262,238,811,523,6171
Sep 3, 20261,913,443,637,1451
Sep 2, 20261,728,912,524,2471
Sep 1, 20261,633,618,836,2371
Aug 31, 20261,591,945,119,6711
Aug 30, 20261,439,645,900,1601
Aug 29, 20261,372,084,924,9131
Aug 28, 20261,605,564,470,1061
Aug 27, 20262,001,383,413,5261
Aug 26, 20262,406,082,692,5331
Aug 25, 20261,770,607,978,9721
Aug 24, 20261,710,948,125,7231
Aug 23, 20261,390,118,528,3511
Aug 22, 20261,393,318,211,4901
Aug 21, 20261,849,078,827,1921
Aug 20, 20261,825,475,696,4171
Aug 19, 20261,684,920,552,2351
Aug 18, 20261,741,314,505,6341
Aug 17, 20261,691,677,097,9911
Aug 16, 20261,455,626,623,1741
Aug 15, 20261,407,526,668,5961
Aug 14, 20261,618,292,508,1261
Aug 13, 20261,634,182,107,1251
Aug 12, 20261,724,399,168,3961
Aug 11, 20261,763,515,344,0891
Aug 10, 20261,576,754,642,2641
Aug 9, 20261,334,761,681,0261
Aug 8, 20261,231,278,479,1021
Aug 7, 20261,425,197,504,8781
Aug 6, 20261,440,365,965,9401
Aug 5, 20261,258,592,247,7191
Aug 4, 20261,120,041,012,4281
Aug 3, 20261,015,839,531,4511
Aug 2, 2026706,786,292,6251
Aug 1, 2026492,645,891,6781
Jul 31, 2026117,062,075,3491

Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
deepseek/deepseek-v4-flash-0731Observed
Context
1,048,576
Maximum output
943,718
Tokenizer
DeepSeek
Input
text
Output
text
Moderation
No
Added to OpenRouter
2026-07-31
Base URLhttps://openrouter.ai/api/v1
Model IDdeepseek/deepseek-v4-flash-0731
Version IDdeepseek/deepseek-v4-flash-20260731
Weights IDdeepseek-ai/DeepSeek-V4-Flash-0731

Reasoning

Required
No
Enabled by default
Yes
Default effort
high
Supported efforts
max, high, low

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • parallel_tool_calls
  • presence_penalty
  • reasoning
  • reasoning_effort
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_a
  • top_k
  • top_logprobs
  • top_p

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does DeepSeek V4 Flash 0731 cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer DeepSeek V4 Flash 0731?

There are 94 cataloged offers across 54 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,000,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Resources

MIT
Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

  • · 39ed45961fb5
  • · 5420dba9e29f