Skip to content
Model Season every model has a season

DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-20260813
DeepSeekChinaOpen weights

The 21st most-used model on the router over the last 7 days, with 0.91% of tokens. Weekly share peaked at 1.1% in the week of Aug 17, 2026, with 3.7T tokens processed since Aug 10, 2026.

Launch
Aug 12, 2026
Context
1M tokens
Modality
text → text
Reasoning
yes
License
Open weights
Input
$0.66 / 1M
Output
$1.98 / 1M
Share, last 7 days
0.91%
21st of 61 · Sep 4, 2026 to Sep 10, 2026
Peak weekly share
1.1%
week of Aug 17, 2026
Cumulative tokens
3.7T
since the week of Aug 10, 2026
Weeks in the top 10
0
of 4 weeks with volume

Weekly token share

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

0.0%0.2%0.4%0.6%0.8%1.0%1.2%Aug 10Aug 17Aug 24Aug 31peak 1.1% on Aug 17, 2026
See the numbers
WeekShare
Aug 31, 20260.896%
Aug 24, 20260.961%
Aug 17, 20261.062%
Aug 10, 20260.819%

Debuted in the week of Aug 10, 2026 and peaked at 1.1% 1 week later. The latest full week came in at 0.90%, 84% of peak.

What this model is used for new

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

Ranks among the leaders in 2 of the 29 classified tasks. Its largest share is in security audit, 3.6% of the task's tokens; in the heaviest task where it appears, roleplay and fiction (3.2% of classified volume), it holds 2.0%.

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
Ionstream$0.66$1.981Mnot reportedyes
DeepSeek$0.66$1.981Mnot reportedno
Novita$0.99$2.971Mfp8yes
StreamLake$1.05$3.151.02Mnot reportedno
GMICloud$1.06$3.171Mfp8no
NextBit$1.12$3.371Mfp8yes
Alibaba$1.12$3.371Mnot reportedno
DeepInfra$1.30$2.601Mfp8yes
CoreWeave$1.31$3.961Mfp8yes
Baidu$1.32$3.961Mfp8no
Sail Research$1.32$3.961Mfp4yes
BaseTen$1.32$3.961Mfp4yes
Parasail$1.32$3.961Mfp8yes
Together$1.32$3.961Mnot reportedyes
DigitalOcean$1.32$3.961Mnot reportedyes
SiliconFlow$1.32$3.961Mfp8yes
BaseTen$1.32$3.961Mfp4yes
Cloudflare$1.32$3.961Mnot reportedno
Fireworks$1.32$3.961Mnot reportedyes
Phala$1.45$4.361Mnot reportedyes

20 endpoints across 19 providers, with input from $0.66 to $1.45 per 1M tokens. 14 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
36.3
22nd of 82
Coding
68.8
27th of 111
Agents
42.3
18th of 86

GPQA Diamond 88.9%

$0.13 per task, 792 tasks. 20th of 131 evaluated. Median of evaluated models: 80.2%, $0.024 per task.

τ-bench verified, airline 78.0%

$0.11 per task, 150 tasks. 8th 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 0423DeepSeekDeepSeek3.9%$0.1111M24.819
DeepSeek V4 Pro 0813this pageDeepSeekDeepSeek0.91%$0.991M36.30

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.