Skip to content
Model Season every model has a seasonRadarLabs

DeepSeek V4 Pro 0423

deepseek/deepseek-v4-pro-20260423
DeepSeekChinaOpen weights

The 36th most-used model on the router over the last 7 days, with 0.34% of tokens. Weekly share peaked at 5.8% in the week of Jul 27, 2026, with 43T tokens processed since Apr 20, 2026.

Launch
Apr 24, 2026
Context
1M tokens
Modality
text → text
Reasoning
yes
License
Open weights
Input
$0.798 / 1M
Output
$1.60 / 1M
Share, last 7 days
0.34%
36th of 63 · Oct 19, 2026 to Oct 25, 2026
Peak weekly share
5.8%
week of Jul 27, 2026
Cumulative tokens
43T
since the week of Apr 20, 2026
Weeks in the top 10
16
of 27 weeks with volume

Weekly token share

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

0%2%4%6%8%May '26JunJulAugSepOctpeak 5.8% on Jul 27, 2026
See the numbers
WeekShare
Oct 19, 20260.342%
Oct 12, 20260.398%
Oct 5, 20260.427%
Sep 28, 20260.441%
Sep 21, 20260.511%
Sep 14, 20260.817%
Sep 7, 20261.037%
Aug 31, 20261.085%
Aug 24, 20261.565%
Aug 17, 20261.982%
Aug 10, 20263.631%
Aug 3, 20263.783%
Jul 27, 20265.773%
Jul 20, 20265.465%
Jul 13, 20264.318%
Jul 6, 20265.369%
Jun 29, 20265.052%
Jun 22, 20264.369%
Jun 15, 20265.432%
Jun 8, 20264.387%
Jun 1, 20264.698%
May 25, 20263.941%
May 18, 20263.719%
May 11, 20263.318%
May 4, 20263.170%
Apr 27, 20261.724%
Apr 20, 20260.106%

Debuted in the week of Apr 20, 2026 and peaked at 5.8% 14 weeks later. The latest full week came in at 0.34%, 6% of peak.

What this model is used for new

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

This model is not among the leaders in any of the 29 tasks classified in the Oct 24, 2026 snapshot. That does not mean it goes unused: the source lists only the largest models in each task.

Snapshot of the rolling 7-day window through Oct 24, 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
Baidu$0.208$0.4161Mfp8no
StreamLake$0.209$0.4181.02Mfp8no
Relace$0.90$1.501Mfp4yes
GMICloud$0.957$1.911Mfp8no
DigitalOcean$1.04$2.091Mnot reportedyes
Reka$1.05$2.101Mnot reportedyes
Cloudflare$1.15$2.551Mnot reportedyes
DeepInfra$1.30$2.601Mfp8yes
Alibaba$1.42$2.831Mfp8no
SiliconFlow$1.50$3.131Mfp8yes
Alibaba$1.56$3.121Mfp8no
Novita$1.60$3.201Mfp8yes
Venice$1.65$3.301Mnot reportedyes
AtlasCloud$1.68$3.381Mfp4no
Azure$1.91$3.831Mnot reportedyes

15 endpoints across 14 providers, with input from $0.208 to $1.91 per 1M tokens. 9 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
30.4
50th of 199
Coding
59.4
37th of 109
Agents
26.3
32nd of 85

GPQA Diamond 86.9%

$0.038 per task, 1584 tasks. 60th of 169 evaluated. Median of evaluated models: 83.4%, $0.025 per task.

τ-bench verified, airline 76.6%

$0.05 per task, 450 tasks. 21st of 150 evaluated. Median of evaluated models: 71.2%, $0.064 per task.

Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Oct 25, 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-6 LunaOpenAIOpenAI4.4%$0.201M38.15
Claude Opus 5.5AnthropicAnthropic4.4%$8.001M57.63
jev-1.13TypesafeTypesafe1.6%———0
GPT-6.1 SolOpenAIOpenAI1.5%$4.001M51.80
Muse Spark 1.3 ContributorMetaMeta1.5%$0.1251M—0
Open weights
DeepSeek V4.1 Flash 1017DeepSeekDeepSeek17.9%$0.2631M39.51
DeepSeek V4.1 FlashDeepSeekDeepSeek9.6%$0.2651M24.77
MiniMax M3.1 FlashMiniMaxMiniMax7.7%$0.2631M42.71
GLM 5.3 FlashZ.ai (GLM)Z.ai (GLM)7.0%$0.2371M41.89
Hy4 previewTencentTencent4.8%$1.251M—8
DeepSeek V4 Pro 0423this pageDeepSeekDeepSeek0.34%$0.9971M30.416

Share over the last 7 days (Oct 19, 2026 to Oct 25, 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.