Skip to content
Model Season every model has a seasonRadar

DeepSeek V4.1 Flash 1017

deepseek/deepseek-v4.1-flash-20261017
DeepSeekChinaOpen weights

The most-used model on the router over the last 7 days, with 14.9% of tokens. Weekly share peaked at 2.3% in the week of Oct 12, 2026, with 3.7T tokens processed since Oct 12, 2026.

Launch
Oct 17, 2026
Context
1M tokens
Modality
text and image → text
Reasoning
yes
License
Open weights
Input
$0.15 / 1M
Output
$0.60 / 1M
Share, last 7 days
14.9%
1st of 62 · Oct 17, 2026 to Oct 23, 2026
Peak weekly share
2.3%
week of Oct 12, 2026
Cumulative tokens
3.7T
since the week of Oct 12, 2026
Weeks in the top 10
0
of 1 week with volume

Weekly token share

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

Only one full week so far: 2.3% of volume in the week of Oct 12, 2026. The chart appears from the second week on.

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 security audit, 44.6% of the task's tokens; in the heaviest task where it appears, workflow execution (23.4% of classified volume), it holds 17.1%.

Snapshot of the rolling 7-day window through Oct 23, 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$0.02$1.001Mfp4yes
Relace$0.07$0.501Mnot reportedyes
DeepInfra$0.078$0.2351Mfp8yes
InferenceNet$0.08$0.501Mfp8yes
InferenceNet$0.08$0.501Mfp8yes
Reka$0.08$0.801Mnot reportedyes
DeepInfra$0.098$0.2941Mfp8yes
Cloudflare$0.10$0.601Mnot reportedyes
Sail Research$0.101$0.151Mfp4yes
Sail Research$0.101$0.151Mfp4yes
Wafer$0.13$0.501Mmxfp4yes
Decart$0.137$0.5461Mfp4yes
DeepInfra$0.147$0.4411Mfp8yes
DeepSeek$0.15$0.601Mnot reportedno
Makora$0.15$1.201Mfp8yes
GMICloud$0.18$0.721Mfp8no
AtlasCloud$0.195$0.781Mfp8no
Fireworks$0.21$0.841Mnot reportedyes
Ionstream$0.22$0.601Mnot reportedyes
DigitalOcean$0.225$0.901Mnot reportedyes
Novita$0.24$0.961Mfp8yes
Modal$0.25$1.001Mnot reportedyes
Baidu$0.28$1.131Mfp8no
Crusoe$0.29$1.201Mfp8yes
Nebius$0.30$1.201Mfp8yes
Phala$0.30$1.201Mnot reportedyes
SiliconFlow$0.30$1.201Mfp8yes
Together$0.30$1.201Mnot reportedyes
Fireworks$0.30$1.201Mnot reportedyes
PrimeIntellect$0.30$1.201Mnot reportedyes
BaseTen$0.30$1.201Mnot reportedyes
Parasail$0.30$1.201Mfp8yes
Alibaba$0.33$1.321Mnot reportedno
Morph$0.454$0.601Mfp8yes

34 endpoints across 29 providers, with input from $0.02 to $0.454 per 1M tokens. 29 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
39.5
31st of 199
Coding
no index
not published
Agents
no index
not published

GPQA Diamond 90.7%

$0.01 per task, 198 tasks. 25th of 169 evaluated. Median of evaluated models: 83.4%, $0.025 per task.

τ-bench verified, airline 76.3%

$0.0069 per task, 100 tasks. 23rd of 150 evaluated. Median of evaluated models: 71.3%, $0.065 per task.

Artificial Analysis indexes, exposed by the catalog; benchmarks run by the source and archived on Oct 24, 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
Claude Opus 5.5AnthropicAnthropic4.5%$8.001M57.62
GPT-6 LunaOpenAIOpenAI3.8%$0.201M38.14
Muse Spark 1.3 ContributorMetaMeta1.7%$0.1251M—0
jev-1.13TypesafeTypesafe1.6%———0
Claude Haiku 5.5AnthropicAnthropic1.5%$0.201M43.40
Open weights
DeepSeek V4.1 Flash 1017this pageDeepSeekDeepSeek14.9%$0.2631M39.50
DeepSeek V4.1 FlashDeepSeekDeepSeek11.5%$0.2651M24.76
MiniMax M3.1 FlashMiniMaxMiniMax7.7%$0.2631M42.70
GLM 5.3 FlashZ.ai (GLM)Z.ai (GLM)6.6%$0.2371M41.88
Hy4 previewTencentTencent4.9%$1.251M—7

Share over the last 7 days (Oct 17, 2026 to Oct 23, 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.