Skip to content
Model Season every model has a season

DeepSeek V4 Flash 0423

deepseek/deepseek-v4-flash-20260423
DeepSeekChinaOpen weights

The 6th most-used model on the router over the last 7 days, with 3.9% of tokens. Weekly share peaked at 12.7% in the week of Jul 27, 2026, with 84T tokens processed since Apr 20, 2026.

Launch
Apr 24, 2026
Context
1M tokens
Modality
text → text
Reasoning
yes
License
Open weights
Input
$0.089 / 1M
Output
$0.177 / 1M
Share, last 7 days
3.9%
6th of 61 · Sep 4, 2026 to Sep 10, 2026
Peak weekly share
12.7%
week of Jul 27, 2026
Cumulative tokens
84T
since the week of Apr 20, 2026
Weeks in the top 10
19
of 20 weeks with volume

Weekly token share

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

0%5%10%15%May '26JunJulAugpeak 12.7% on Jul 27, 2026
See the numbers
WeekShare
Aug 31, 20264.493%
Aug 24, 20264.605%
Aug 17, 20265.846%
Aug 10, 20266.411%
Aug 3, 20268.517%
Jul 27, 202612.714%
Jul 20, 202610.976%
Jul 13, 20268.578%
Jul 6, 20269.927%
Jun 29, 202611.429%
Jun 22, 20269.970%
Jun 15, 202610.578%
Jun 8, 20269.892%
Jun 1, 202610.199%
May 25, 20269.772%
May 18, 202611.941%
May 11, 20267.802%
May 4, 20264.317%
Apr 27, 20262.955%
Apr 20, 20260.723%

Debuted in the week of Apr 20, 2026 and peaked at 12.7% 14 weeks later. The latest full week came in at 4.5%, 35% of peak.

What this model is used for new

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

Plus 15 more tasks with a smaller share.

Ranks among the leaders in 27 of the 29 classified tasks. Its largest share is in roleplay and fiction, 18.3% of the task's tokens; in the heaviest task where it appears, workflow execution (24.6% of classified volume), it holds 2.7%.

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
DigitalOcean$0.068$0.1681Mnot reportedyes
StreamLake$0.089$0.1771.02Mfp8no
DeepInfra$0.09$0.181Mfp8yes
GMICloud$0.091$0.1821Mfp8no
Wafer$0.10$0.251Mnot reportedyes
SiliconFlow$0.13$0.281Mfp8yes
Alibaba$0.134$0.2681Mfp8no
Venice$0.138$0.2751Mnot reportedyes
Baidu$0.14$0.281Mfp8no
Novita$0.14$0.281Mfp8yes
AtlasCloud$0.14$0.281Mfp4no
Parasail$0.14$0.281Mfp8yes
NextBit$0.15$0.351Mfp8yes
Mancer 2$0.19$0.501Mfp8yes
Phala$0.20$0.401Mnot reportedyes
Azure$0.21$0.561Mnot reportedyes

16 endpoints across 16 providers, with input from $0.068 to $0.21 per 1M tokens. 11 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
24.8
41st of 82
Coding
52.0
51st of 111
Agents
27.9
29th of 86

GPQA Diamond 86.6%

$0.0036 per task, 3366 tasks. 27th of 131 evaluated. Median of evaluated models: 80.2%, $0.024 per task.

τ-bench verified, airline 75.1%

$0.0085 per task, 1150 tasks. 33rd 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 0731DeepSeekDeepSeek10.0%$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 0423this pageDeepSeekDeepSeek3.9%$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.