Skip to content
Model Season every model has a season

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-20260731
DeepSeekChinaOpen weights

The 3rd most-used model on the router over the last 7 days, with 10.0% of tokens. Weekly share peaked at 14.8% in the week of Aug 10, 2026, with 58T tokens processed since Jul 27, 2026.

Launch
Jul 31, 2026
Context
1.31M tokens
Modality
text → text
Reasoning
yes
License
Open weights
Input
$0.065 / 1M
Output
$0.18 / 1M
Share, last 7 days
10.0%
3rd of 61 · Sep 4, 2026 to Sep 10, 2026
Peak weekly share
14.8%
week of Aug 10, 2026
Cumulative tokens
58T
since the week of Jul 27, 2026
Weeks in the top 10
5
of 6 weeks with volume

Weekly token share

Share of the router's weekly volume, since the first week with volume

0%5%10%15%20%Jul 27Aug 3Aug 10Aug 17Aug 24Aug 31peak 14.8% on Aug 10, 2026
See the numbers
WeekShare
Aug 31, 202610.705%
Aug 24, 202610.891%
Aug 17, 202612.397%
Aug 10, 202614.840%
Aug 3, 202612.783%
Jul 27, 20262.318%

Debuted in the week of Jul 27, 2026 and peaked at 14.8% 2 weeks later. The latest full week came in at 10.7%, 72% of peak.

What this model is used for new

Tasks where the model ranks among the leaders, and its share of each

Plus 17 more tasks with a smaller share.

Ranks among the leaders in 29 of the 29 classified tasks. Its largest share is in finance and trading, 26.1% of the task's tokens; in the heaviest task where it appears, workflow execution (24.6% of classified volume), it holds 9.9%.

Snapshot of the rolling 7-day window through Sep 10, 2026. Share: the model's tokens in the task over the task's total tokens. Weight: the task's share of classified volume.

Where to run it

Endpoints in the source's catalog, from cheapest to most expensive on input

ProviderInputOutputContextQuantizationZero retention
OpenInference$0.05$0.161Mfp8yes
DeepInfra$0.06$0.181Mfp8yes
Relace$0.065$0.181Mfp4yes
Sail Research$0.065$0.301Mfp4yes
DigitalOcean$0.08$0.2521Mnot reportedyes
Makora$0.09$0.1951Mnot reportedyes
Wafer$0.10$0.251Mnot reportedyes
Reka$0.11$0.66256kfp4yes
StreamLake$0.119$0.3561.02Mfp8no
Inceptron$0.123$0.3311Mfp4yes
Morph$0.123$0.3481Mbf16yes
BaseTen$0.13$0.261Mfp8yes
BaseTen$0.13$0.261Mfp8yes
CoreWeave$0.13$0.28256kfp8yes
Together$0.14$0.281Mnot reportedyes
Parasail$0.14$0.281Mfp8yes
Mancer 2$0.165$0.501Mfp8yes
Venice$0.175$0.351Mnot reportedyes
Fireworks$0.22$0.661Mnot reportedyes
SiliconFlow$0.22$0.661Mfp8yes
GMICloud$0.286$0.8581Mfp4no
NextBit$0.352$1.061Mfp8yes
Alibaba$0.352$1.061Mnot reportedno
Novita$0.409$1.231Mfp8yes
Phala$0.44$1.321Mnot reportedyes
Baidu$0.44$1.321Mfp8no
AtlasCloud$0.44$1.321Mfp4no
Cloudflare$0.44$1.321.31Mnot reportedno

28 endpoints across 27 providers, with input from $0.05 to $0.44 per 1M tokens. 22 offer zero data retention.

Prices in US dollars per million tokens, from the latest archived endpoint catalog.

Benchmarks

Artificial Analysis indexes and benchmarks run by the source, with cost per task

Intelligence
34.5
23rd of 82
Coding
69.1
26th of 111
Agents
41.7
20th of 86

GPQA Diamond 85.2%

$0.0091 per task, 990 tasks. 37th of 131 evaluated. Median of evaluated models: 80.2%, $0.024 per task.

τ-bench verified, airline 73.2%

$0.0092 per task, 250 tasks. 46th of 122 evaluated. Median of evaluated models: 70.7%, $0.056 per task.

Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Sep 11, 2026. The gray mark is the median of evaluated models.

Against the week's largest models

The five largest proprietary and five largest open-weights models over the last 7 days

ModelLab7-day shareBlended priceContextIntelligenceWeeks in top 10
Proprietary
GPT-5.6 LunaOpenAIOpenAI11.5%$0.451M37.56
Gemini 3.8 FlashGoogleGoogle2.1%$1.501M41.20
Muse Spark 1.3 ContributorMetaMeta1.5%$0.1251M0
Claude Opus 5AnthropicAnthropic1.4%$10.001M50.71
GPT-5.6 SolOpenAIOpenAI1.4%$4.001M47.10
Open weights
Hy4 previewTencentTencent15.5%$1.251M1
DeepSeek V4 Flash 0731this pageDeepSeekDeepSeek10.0%$0.0941.31M34.55
GLM 5.3 FlashZ.ai (GLM)Z.ai (GLM)10.0%$0.2371.31M41.92
MiMo-V2.5XiaomiXiaomi4.2%$0.1751M22.315
DeepSeek V4 Flash 0423DeepSeekDeepSeek3.9%$0.1111M24.819

Share over the last 7 days (Sep 4, 2026 to Sep 10, 2026). Blended price in US dollars per million tokens, weighted 75% input and 25% output. A dash means the number is not published, not zero.

What this page doesn't say. Share here is a slice of one router's traffic, where the deciding factor is usually price per token. It is not market, revenue or user share, and it does not tell you which model fits your workload.