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
57
Context
1,000,000
Output limit
384,000
Knowledge
2025-05
Release
2026-07-31
Updated
—
Weights
Open
Input
text
Output
text
Capabilities
—

Providers

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

105 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
AIHubMix
deepseek-v4-flash-0731
1,000,000384,000— / ————
View
AIHubMix
deepseek-v4-flash-0731-fast
1,000,000384,000— / ————
View
Alibaba
deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Alibaba Token Plan
deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Alibaba Token Plan (China)
deepseek-v4-flash-0731
1,000,000384,000— / ————
View
AMD
DeepSeek-V4-Flash
1,048,576384,000— / ————
View
Arcee
deepseek/deepseek-v4-flash-latest
1,048,576384,000— / ————
View
Baseten
deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000— / ————
View
Bothub
deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Boundless
dsv4
1,048,576384,000— / ————
View
BytePlus ModelArk
deepseek-v4-flash-ga-260731
1,000,000384,000— / ————
View
Chutes
deepseek-ai/DeepSeek-V4-Flash-0731-TEE
1,048,576131,072— / ————
View
Cloudflare Workers AI
@cf/deepseek-ai/deepseek-v4-flash-0731
1,048,5761,048,576— / ————
View
CoreWeave
deepseek-ai/DeepSeek-V4-Flash-0731
262,144262,144— / ————
View
Cortecs
deepseek-v4-flash-0731
1,048,5761,048,576— / ————
View
Deep Infra
deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000— / ————
View
DevPass (LLM Gateway)
deepseek-v4-flash-0731
1,050,000384,000— / ————
View
DigitalOcean
deepseek-v4-flash-0731
1,048,5761,048,576— / ————
View
Eden AI
cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731
1,048,576384,000— / ————
View
Eden AI
sference/deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000— / ————
View
Eden AI
greenpt/deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Eden AI
flexai/DeepSeek-V4-Flash-0731
1,048,576384,000— / ————
View
Eden AI
tensorx/deepseek/deepseek-v4-flash-0731
1,048,576384,000— / ————
View
Eden AI
nebius/deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000— / ————
View
Eden AI
qwen/deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Eden AI
scaleway/deepseek-v4-flash-0731
256,000384,000— / ————
View
Eden AI
flexai/DeepSeek-V4-Flash-0731@eu
1,048,576384,000— / ————
View
Eden AI
deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000— / ————
View
Eden AI
arkanecloud/deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000— / ————
View
EmpirioLabs AI
deepseek-v4-flash-0731
1,000,000393,216— / ————
View
engy
deepseek-v4-flash-0731
1,048,576128,000— / ————
View
GreenPT
deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Hugging Face
deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000— / ————
View
Inceptron
deepseek-ai/DeepSeek-V4-Flash-0731
1,048,5761,048,576— / ————
View
Kilo Gateway
deepseek/deepseek-v4-flash-0731
1,048,576943,718— / ————
View
LLM Gateway
tencent/deepseek-v4-flash-0731
1,000,000393,216— / ————
View
LLM Gateway
bytedance/deepseek-v4-flash-0731
1,048,576393,216— / ————
View
LLM Gateway
canopywave/deepseek-v4-flash-0731
1,000,000384,000— / ————
View
LLM Gateway
cloudflare/deepseek-v4-flash-0731
1,048,576393,216— / ————
View
LLM Gateway
deepinfra/deepseek-v4-flash-0731
1,000,000393,216— / ————
View
LLM Gateway
alibaba/deepseek-v4-flash-0731
1,000,000393,216— / ————
View
LLM Gateway
novita/deepseek-v4-flash-0731
1,050,000393,216— / ————
View
LLM Gateway
baidu/deepseek-v4-flash-0731
1,048,576131,072— / ————
View
Melious
deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Merge Gateway
deepseek/deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Merge Gateway
deepseek/deepseek-v4-flash-0731-fast
1,000,000384,000— / ————
View
Moark
deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Morph
morph-dsv4flash
1,048,5761,048,576— / ————
View
Munito AI
deepseek-ai/deepseek-v4-flash
1,048,576943,718— / ————
View
Munito AI (EU)
deepseek-ai/deepseek-v4-flash
1,048,576943,718— / ————
View
NanoGPT
deepseek/deepseek-v4-flash-0731:thinking
1,048,576131,072— / ————
View
NanoGPT
deepseek/deepseek-v4-flash-0731
1,048,576131,072— / ————
View
Neuralwatt
deepseek-v4-flash-speed
1,048,560393,216— / ————
View
Novita AI
deepseek/deepseek-v4-flash-0731
1,048,576393,216— / ————
View
Ofox
deepseek/deepseek-v4-flash-0731
1,000,000384,000— / ————
View
OpenCode
deepseek-v4-flash-free
200,000128,000— / ————
View
OpenCode
deepseek-v4-flash
1,000,000384,000— / ————
View
OpenReason
deepseek-ai/deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Alibabavia OpenRouter
deepseek/deepseek-v4-flash-0731
unknown
1,000,000393,216$0.374 / $1.122YesYesYes
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$0.1015 / $0.60YesYesYes
View
Mancer 2via OpenRouter
deepseek/deepseek-v4-flash-0731
fp8
1,048,576943,718$0.20 / $0.60YesYesYes
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$0.01089 / $0.27YesYesYes
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$0.0103 / $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$0.10 / $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$0.088 / $0.264YesYesNo
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$0.13 / $0.26YesYesYes
View
Wafervia OpenRouter
deepseek/deepseek-v4-flash-0731
unknown
1,048,576943,718$0.13 / $0.23YesYesYes
View
OrcaRouter
deepseek/deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Perplexity Agent
deepseek/deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Prime Inference
deepseek/deepseek-v4-flash-0731
1,048,57665,536— / ————
View
Requesty
deepseek-v4-flash-0731
1,048,576131,072— / ————
View
Requesty
deepseek-v4-flash-0731@eu
1,048,576131,072— / ————
View
RunInfra
deepseek-ai/DeepSeek-V4-Flash-0731
1,048,57632,768— / ————
View
Scaleway
deepseek-v4-flash-0731
256,00032,768— / ————
View
SCNet Token Plan
DeepSeek-V4-Flash-0731
1,000,000384,000— / ————
View
SiliconFlow
deepseek-ai/DeepSeek-V4-Flash-0731
1,000,000384,000— / ————
View
Standard Compute
deepseek/deepseek-v4-flash-0731
1,000,00050,000— / ————
View
TensorX
deepseek/deepseek-v4-flash-0731
1,048,576384,000— / ————
View
Together AI
deepseek-ai/DeepSeek-V4-Flash-0731
1,048,576384,000— / ————
View
Umans AI
umans-deepseek-v4-flash-0731
1,048,576393,215— / ————
View
Umans AI Coding Plan
umans-deepseek-v4-flash-0731
1,048,576393,215— / ————
View
Venice AI
deepseek-v4-flash-0731
1,000,000262,144— / ————
View
Venice AI
deepseek-v4-flash-0731-fast
1,000,00032,768— / ————
View
Vercel AI Gateway
deepseek/deepseek-v4-flash-0731
1,000,000384,000— / ————
View
Vivgrid
deepseek-v4-flash
1,000,000384,000— / ————
View
Volcengine Ark
deepseek-v4-flash-ga-260731
1,000,000384,000— / ————
View
Vultr
deepseek-v4-flash-0731
1,048,576384,000— / ————
View
Wally
deepseek-v4-flash-0731
1,048,57665,536— / ————
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$0.0103Per 1M input tokens
Output from$0.18Per 1M output tokens
Available offers105Across 57 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
$0.0103$1.28
OpenInferenceopen-inference/fp4
$0.01089$0.27
Sail Researchsail-research/us
$0.019$0.42
Rekareka
$0.021$0.528
DeepInfradeepinfra/fp8
$0.06$0.18
StreamLakestreamlake/fp8
$0.088$0.264
Sail Researchsail-research/fp4
$0.10$0.30
Inceptroninceptron/fp4
$0.1015$0.60
DigitalOceandigitalocean
$0.119$0.238
BaseTenbaseten/fp8
$0.13$0.26
deepseek/deepseek-v4-flash-0731Observed
Input
$0.0099
Output
$1.28
Cache read
$0.0099
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Alibabaalibaba/us-east-1$0.374$1.122$0.0374—
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$0.1015$0.60$0.027—
Mancer 2mancer/fp8$0.20$0.60——
Novitanovita/fp8$0.4092$1.2276$0.02604—
OpenInferenceopen-inference/fp4$0.01089$0.27$0.00792—
Parasailparasail/fp8$0.14$0.28$0.05—
Phalaphala$0.308$0.924$0.0196—
Rekareka$0.021$0.528$0.0056—
Relacerelace/fp4$0.0103$1.28$0.0103—
Sail Researchsail-research/us$0.019$0.42$0.012—
Sail Researchsail-research/fp4$0.10$0.30$0.03—
SiliconFlowsiliconflow/fp8$0.22$0.66$0.028—
StreamLakestreamlake/fp8$0.088$0.264$0.0028—
Togethertogether$0.14$0.28$0.03—
Venicevenice$0.13$0.26$0.028—
Waferwafer/fast$0.13$0.23$0.12—

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/us-east-1
2,131–7,110.68 ms
Alibabaalibaba
1,224–5,092 ms
AtlasCloudatlas-cloud/fp4
1,669–5,815.86 ms
Baidubaidu/fp8
964–11,320.4 ms
Cloudflarecloudflare
3,288.5–12,183.46 ms
Coherecohere
398–10,249.36 ms
All latency percentiles 25 endpoints
EndpointP50P75P90P99
Alibabaalibaba/us-east-12,131 ms4,470 ms5,333.6 ms7,110.68 ms
Alibabaalibaba1,224 ms1,586 ms1,884 ms5,092 ms
AtlasCloudatlas-cloud/fp41,669 ms2,045 ms3,170.8 ms5,815.86 ms
Baidubaidu/fp8964 ms1,266 ms1,696 ms11,320.4 ms
Cloudflarecloudflare3,288.5 ms4,183 ms5,016.3 ms12,183.46 ms
Coherecohere398 ms818 ms1,752.7 ms10,249.36 ms
CoreWeavecoreweave/fp8451 ms765.25 ms1,497 ms5,551.22 ms
DeepInfradeepinfra/fp8804.5 ms1,358.25 ms2,514.8 ms7,782.35 ms
DigitalOceandigitalocean745 ms1,079 ms1,649 ms6,571.27 ms
GMICloudgmicloud/fp81,842 ms2,227 ms2,838 ms6,016.26 ms
Inceptroninceptron/fp4837 ms1,620 ms3,457.6 ms38,262.68 ms
Mancer 2mancer/fp81,046.5 ms1,668 ms2,621.2 ms6,660.53 ms
Novitanovita/fp82,067 ms2,564.75 ms3,370.3 ms11,237.36 ms
OpenInferenceopen-inference/fp41,574.5 ms2,566 ms4,056 ms9,361.54 ms
Parasailparasail/fp8732 ms1,012 ms1,954 ms15,893.29 ms
Phalaphala4,010.5 ms5,803 ms8,769.1 ms46,427.22 ms
Rekareka594 ms890.25 ms2,612.6 ms20,989.52 ms
Relacerelace/fp4594 ms1,009 ms1,838.9 ms8,630.43 ms
Sail Researchsail-research/us2,036 ms2,668.25 ms3,343.5 ms7,744.63 ms
Sail Researchsail-research/fp42,221 ms2,822 ms3,617.9 ms7,263.95 ms
SiliconFlowsiliconflow/fp81,300 ms1,567 ms2,025.8 ms5,020.48 ms
StreamLakestreamlake/fp81,233 ms1,931 ms2,918 ms8,598.5 ms
Togethertogether971.5 ms2,895 ms6,348.9 ms31,151.3 ms
Venicevenice1,202 ms1,847.5 ms3,237 ms50,473 ms
Waferwafer/fast913 ms1,556 ms2,356.9 ms7,567.97 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Alibabaalibaba/us-east-1
74.5–186.23 t/s
Alibabaalibaba
120–195 t/s
AtlasCloudatlas-cloud/fp4
51–141.11 t/s
Baidubaidu/fp8
62–179.77 t/s
Cloudflarecloudflare
40–77 t/s
Coherecohere
125–337 t/s
All throughput percentiles 25 endpoints
EndpointP50P75P90P99
Alibabaalibaba/us-east-174.5 t/s112.25 t/s139.1 t/s186.23 t/s
Alibabaalibaba120 t/s149 t/s167 t/s195 t/s
AtlasCloudatlas-cloud/fp451 t/s69 t/s90 t/s141.11 t/s
Baidubaidu/fp862 t/s84.25 t/s115 t/s179.77 t/s
Cloudflarecloudflare40 t/s51 t/s66 t/s77 t/s
Coherecohere125 t/s162 t/s207 t/s337 t/s
CoreWeavecoreweave/fp8114 t/s141 t/s173 t/s230.09 t/s
DeepInfradeepinfra/fp837 t/s49 t/s60 t/s86 t/s
DigitalOceandigitalocean45 t/s49 t/s52 t/s57.09 t/s
GMICloudgmicloud/fp863 t/s77 t/s100 t/s161 t/s
Inceptroninceptron/fp455 t/s90 t/s126 t/s211 t/s
Mancer 2mancer/fp844 t/s54 t/s65.4 t/s89.56 t/s
Novitanovita/fp869 t/s80 t/s88 t/s165.14 t/s
OpenInferenceopen-inference/fp420 t/s23 t/s26 t/s29 t/s
Parasailparasail/fp882.5 t/s129 t/s175 t/s277.09 t/s
Phalaphala53 t/s74.25 t/s91.9 t/s140 t/s
Rekareka143 t/s208 t/s270 t/s389.09 t/s
Relacerelace/fp457 t/s103 t/s157 t/s261 t/s
Sail Researchsail-research/us38 t/s45 t/s54 t/s78 t/s
Sail Researchsail-research/fp438 t/s44 t/s51 t/s71 t/s
SiliconFlowsiliconflow/fp829 t/s33 t/s57 t/s103.67 t/s
StreamLakestreamlake/fp846 t/s62 t/s74 t/s94 t/s
Togethertogether55 t/s79 t/s107 t/s172 t/s
Venicevenice38 t/s47 t/s59 t/s84.2 t/s
Waferwafer/fast87 t/s107 t/s132 t/s211.09 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 · 26 endpoints
Endpoint5 minutes30 minutes24 hours
Alibabaalibaba/us-east-1
Alibabaalibaba
AtlasCloudatlas-cloud/fp4
Baidubaidu/fp8
BaseTenbaseten/fp8
Cloudflarecloudflare
Coherecohere
CoreWeavecoreweave/fp8
DeepInfradeepinfra/fp8
DigitalOceandigitalocean
GMICloudgmicloud/fp8
Inceptroninceptron/fp4
Mancer 2mancer/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
models3d1,21448.6%40
modelsasciiart1,09733.3%61
modelscodecategories1,23346.4%44
modelsdataviz1,18441.1%59
modelsgamedev1,21644.6%46
modelssvg1,18645.1%30
modelsuicomponent1,23946.8%42
modelswebsite1,24246.7%44

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%
gpqa diamondDeepSeek: DeepSeek V4 Flash 0731
86.683%
tau bench verified airlineDeepSeek: DeepSeek V4 Flash 0731
73.407%
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
models · svgDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,170 Elo
Details
models · codecategoriesDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,219 Elo
Details
models · datavizDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,169 Elo
Details
models · websiteDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,230 Elo
Details
models · asciiartDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,092 Elo
Details
models · gamedevDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,198 Elo
Details
gpqa diamondDeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-20260731OpenRouter86.683%
Details
models · uicomponentDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,227 Elo
Details
models · 3dDeepSeek-V4-Flash-0731deepseek/deepseek-v4-flash-20260731Design Arena1,188 Elo
Details
tau bench verified airlineDeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-20260731OpenRouter73.407%
Details
Composite indicesDeepSeek V4 Flash 0731 (Max)deepseek/deepseek-v4-flash-20260731Artificial AnalysisIntelligence — · Coding 69.1 · Agentic 41
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 Nov 14, 2026.

Apps & session costs

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

30-day sample · through Nov 1, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Hermes Agentdeepseek/deepseek-v4-flash-202607311 turn
$0.000423
Details
Hermes Agentdeepseek/deepseek-v4-flash-202607312–9 turns
$0.004061
Details
Kilo Codedeepseek/deepseek-v4-flash-202607311 turn
$0.000195
Details
Kilo Codedeepseek/deepseek-v4-flash-202607312–9 turns
$0.00752
Details
Claude Codedeepseek/deepseek-v4-flash-202607311 turn
$0.00083
Details
Claude Codedeepseek/deepseek-v4-flash-2026073150+ turns
$0.173124
Details
Kilo Codedeepseek/deepseek-v4-flash-2026073150+ turns
$0.318302
Details
Kilo Codedeepseek/deepseek-v4-flash-2026073110–49 turns
$0.046219
Details
Hermes Agentdeepseek/deepseek-v4-flash-2026073110–49 turns
$0.034749
Details
Codexdeepseek/deepseek-v4-flash-202607311 turn
$0.000623
Details
Claude Codedeepseek/deepseek-v4-flash-202607312–9 turns
$0.004439
Details
Hermes Agentdeepseek/deepseek-v4-flash-2026073150+ turns
$0.261894
Details
Claude Codedeepseek/deepseek-v4-flash-2026073110–49 turns
$0.033534
Details

Source: OpenRouter, as of Nov 9, 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 usage95,872,826,397,483 reported tokens · 90 days with observations
Aug 16, 2026Nov 13, 2026
Daily observations · 90 days
Date (UTC)Reported tokensReported routes
Nov 13, 2026448,628,565,4191
Nov 12, 2026519,726,952,1971
Nov 11, 2026640,785,679,2631
Nov 10, 2026445,114,275,3661
Nov 9, 2026467,927,734,3101
Nov 8, 2026380,958,157,2861
Nov 7, 2026369,754,037,4311
Nov 6, 2026413,309,761,1351
Nov 5, 2026488,096,267,3181
Nov 4, 2026533,387,596,7591
Nov 3, 2026532,731,720,3811
Nov 2, 2026571,178,343,0521
Nov 1, 2026495,056,452,2891
Oct 31, 2026527,229,571,4411
Oct 30, 2026539,490,740,5781
Oct 29, 2026510,292,934,4171
Oct 28, 2026578,090,099,0451
Oct 27, 2026663,128,246,2931
Oct 26, 2026625,355,522,4441
Oct 25, 2026510,950,291,3931
Oct 24, 2026504,717,030,1001
Oct 23, 2026601,089,481,0701
Oct 22, 2026586,371,963,9951
Oct 21, 2026575,674,647,6141
Oct 20, 2026585,593,798,3571
Oct 19, 2026626,432,649,4051
Oct 18, 2026608,182,877,8461
Oct 17, 2026584,493,642,1311
Oct 16, 2026620,600,893,3731
Oct 15, 2026691,049,828,5631
Oct 14, 2026995,780,142,6531
Oct 13, 2026598,509,158,5681
Oct 12, 2026601,059,076,4901
Oct 11, 2026620,127,280,6061
Oct 10, 2026542,347,269,7021
Oct 9, 2026680,702,210,1151
Oct 8, 2026668,135,877,7491
Oct 7, 2026713,532,318,5931
Oct 6, 2026837,988,232,7871
Oct 5, 2026853,299,292,6801
Oct 4, 2026748,991,224,0991
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

Source: OpenRouter (openrouter.ai/rankings), as of Nov 14, 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 $0.0103 per million input tokens and $0.18 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer DeepSeek V4 Flash 0731?

There are 105 cataloged offers across 57 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: Not reported. Structured output: Not reported. Support can vary by endpoint.

Resources

MIT
Catalog history · 3 recorded revisions

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

  • · 94e2805e2b72
  • · 39ed45961fb5
  • · 5420dba9e29f