Skip to content
Sovyron

DeepSeek V4.1 Flash 1017

deepseek-flash1.1M context1.1M max outputreleased Oct 17, 2026Open weightsReasoningTool calling4 subscription plans →

As of Nov 16, 2026, the cheapest DeepSeek V4.1 Flash 1017 API price is $0.01 per 1M input tokens (Refuseless) and $0.08 per 1M output tokens (Refuseless). DeepSeek V4.1 Flash 1017 is offered by 77 providers in the deepseek-flash family, open weights, reasoning enabled. DeepSeek's own rate is $0.6 per 1M output tokens. One provider lists it as a free-tier offer. It is also included in 4 flat-rate subscription plans, Qwen (Alibaba Cloud) Token Plan Lite from $8/mo.

Cheapest input
$0.01
Cheapest output
$0.08
Official (DeepSeek)
$0.6
output per 1M tokens
Providers
77
offering this model
Spread
45.0×
max / min output
Free offers
1
free-tier offer

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.

DeepSeek V4.1 Flash 1017 API prices by provider in USD per 1M tokens, updated Nov 16, 2026
Refuselessopendeepseek-v4.1-flash-fastCheapest$0.01Cheapest$0.08$0.002—1.0M—
engyopendeepseek-v4.1-flash-1017$0.03$0.12$0.006—1.0M24d agoout +50%
Liquid Inferenceopendeepseek-v4.1-flash-1017$0.059$0.206$0.0026—1.0M—
50Xopendeepseek-ai/DeepSeek-V4.1-Flash-1017$0.064$0.24$0.0012—1.0M—
OpenRouteropendeepseek/deepseek-v4.1-flash-1017$0.038$0.5$0.01—1.0M2d agoout −16.7%
Runcrateopendeepseek-ai/DeepSeek-V4.1-Flash-1017$0.1029$0.3087$0.0031—1.0M—
Prime Inferenceopendeepseek/deepseek-v4.1-flash-1017$0.0437$0.7$0.0024$0.04371.0M7d agoout −41.7%
BytePlus ModelArkopendeepseek-v4-1-flash-economy-261017$0.12$0.48$0.002—1.0M—
WaferopenDeepSeek-V4.1-Flash-1017$0.13$0.5$0.008—1.0M—
NanoGPTopendeepseek/deepseek-v4.1-flash-1017$0.1$0.6$0.0042—1.0M15d agoout −16.7%
DevPass (LLM Gateway)opendeepseek-v4.1-flash-1017$0.135$0.54$0.003—1.1M9d agoout −32.5%
IteraComputeopendeepseek/deepseek-v4.1-flash-1017$0.14$0.55$0.006—1.0M—
BytePlus ModelArkopendeepseek-v4-1-flash-261017$0.15$0.6$0.003—1.0M—
DeepSeekopendeepseek-flash$0.15$0.6$0.003—1.0M—
Doublewordopendeepseek-ai/DeepSeek-V4.1-Flash-1017$0.15$0.6$0.003$0.18751.0M—
Eden AIopenqwen/deepseek-v4.1-flash-1017$0.15$0.6$0.003—1.0M—
Eden AIopentencent/deepseek-v4.1-flash-1017$0.15$0.6$0.003—1.0M—
LLM Gatewayopendeepseek/deepseek-v4.1-flash-1017$0.15$0.6$0.003—1.1M—
LLM Gatewayopentencent/deepseek-v4.1-flash-1017$0.15$0.6$0.003—1.0M—
Merge Gatewayopendeepseek/deepseek-v4.1-flash-1017$0.15$0.6$0.003—1.0M—
Ollama Cloudopendeepseek-v4.1-flash:1017$0.15$0.6$0.003—1.0M—
OpenCode Goopendeepseek-v4.1-flash$0.15$0.6$0.003—1.0M—
TeamoRouteropendeepseek-flash-1017$0.15$0.6$0.003—1.0M—
Umans AIopenumans-deepseek-v4.1-flash-1017$0.15$0.6$0.028—1.0M—
Hopperopendeepseek-v4.1-flash-1017$0.09$0.85$0.007—1.0M—
Morphopenmorph-dsv41flash-1017$0.12$0.8$0.008—1.0M—
Deep Infraopendeepseek-ai/DeepSeek-V4.1-Flash-1017$0.2$0.6$0.006—1.0M—
Eden AIopendeepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017$0.2$0.6$0.006—1.0M—
Entrimopendeepseek-ai/DeepSeek-V4.1-Flash-1017$0.2$0.6$0.005—1.0M—
LLM Gatewayopendeepinfra/deepseek-v4.1-flash-1017$0.2$0.6$0.006—1.0M—
Cortecsopendeepseek-v4.1-flash-1017$0.203$0.609$0.006—1.0M22d agoout −45.3%
ProxyStacks Relayopendeepseek-v4.1-flash$0.18$0.74$0.0039—1.0M—
EmpirioLabs AIopendeepseek-v4-1-flash-1017$0.2$0.8$0.02—1.0M10d agoout −33.3%
LLM Gatewayopenentrim/deepseek-v4.1-flash-1017$0.2$0.8$0.005—1.0M—
ai&opendeepseek-ai/deepseek-v4.1-flash-1017$0.3$0.6$0.02—1.0M—
Wallyopendeepseek-v4.1-flash-1017$0.195$1$0.006—1.0M—
LithosAIopendeepseek-ai/DeepSeek-V4.1-Flash$0.15$1.2$0.003—1.0M—
Modularopendeepseek/deepseek-v4.1-flash-1017$0.17$1.2$0.02—1.0M—
Munito AIopendeepseek-ai/deepseek-v4.1-flash-1017$0.27$1$0.0054—1.0M—
Kitaniopendeepseek/deepseek-v4.1-flash-1017$0.25$1.1$0.006—1.0M—
Kitaniopendeepseek/deepseek-v4.1-flash-1017-thinking$0.25$1.1$0.006—1.0M—
AbliteratedLLMopendeepseek-v4.1-flash-1017$0.27$1.08$0.0054—1.0M—
LLM Gatewayopeninference.net/deepseek-v4.1-flash-1017$0.3$1$0.007—262k—
AKI.IOopendeepseek-v4.1-flash-1017-tl5$0.2791$1.1165$0.1116—1.0M—
NaNopendeepseek-v4-flash$0.2948$1.1794$0.0059—1.0Myesterday
Klavo AIopendeepseek/deepseek-v4.1-flash-1017$0.2907$1.2114$0.0182—1.0M—
Huawei Cloud MAASopendeepseek-v4.1-flash-1017$0.2999$1.1994$0.03—1.0M—
Arceeopendeepseek/deepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M—
Basetenopendeepseek-ai/DeepSeek-V4.1-Flash-1017$0.3$1.2$0.007—1.0M—
CheapestTokenopendeepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M—
Chutesopendeepseek-ai/DeepSeek-V4.1-Flash-1017$0.3$1.2$0.03—1.0M—
Cloudflare Workers AIopen@cf/deepseek-ai/deepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M—
DigitalOceanopendeepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M—
Eden AIopencloudflare/@cf/deepseek-ai/deepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M—
Eden AIopennebius/deepseek-ai/DeepSeek-V4.1-Flash-1017$0.3$1.2$0.3—1.0M—
Eden AIopentogether_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017$0.3$1.2$0.006—1.0M—
Fireworks AIopenaccounts/fireworks/models/deepseek-v4p1-flash-1017$0.3$1.2$0.006—1.0M—
Hugging Faceopendeepseek-ai/DeepSeek-V4.1-Flash-1017$0.3$1.2——1.0M—
Kelnopendeepseek-ai/deepseek-v4.1-flash-1017$0.3$1.2$0.01—1.0M—
Kilo Gatewayopendeepseek/deepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M26d agoout +100%
LLM Gatewayopenalibaba/deepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M—
LLM Gatewayopencloudflare/deepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M—
LLM Gatewayopennovita/deepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M—
LLM Gatewayopentogether-ai/deepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M—
Mistralopendeepseek-v4-1-flash-1017$0.3$1.2$0.007—1.0M—
NEAR AI Cloudopendeepseek-ai/DeepSeek-V4.1-Flash-1017$0.3$1.2$0.006—1.0M—
NEAR AI Cloudopendeepseek/deepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M—
Nebius Token Factoryopendeepseek-ai/DeepSeek-V4.1-Flash-1017$0.3$1.2$0.006—1.0M—
Novita AIopendeepseek/deepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M—
Ofoxopendeepseek/deepseek-v4.1-flash-1017$0.3$1.2$0.006—1.0M—
OpenCodeopendeepseek-v4.1-flash$0.3$1.2$0.006—1.0M—
SCX.aiopenDeepSeek-V4.1-flash-1017$0.3$1.2$0.006—1.0M—
Vercel AI Gatewayopendeepseek/deepseek-v4.1-flash-1017$0.3$1.2$0.007—1.0M16d agoout +300%
CoreWeaveopendeepseek-ai/DeepSeek-V4.1-Flash-1017$0.3$1.2$0.006—1.0M—
Watt CloudopenDeepSeek-V4.1-Flash-1017$0.3$1.2——1.0M—
Charm Hyperopendeepseek-v4.1-flash-1017$0.33$1.31$0.03—1.0M—
Infersiaopendeepseek/deepseek-v4.1-flash-1017$0.35$1.25$0.01—1.0M—
Meliousopendeepseek-v4.1-flash-1017$0.3345$1.338$0.0335—1.0M18d agoout −0.7%
DotHooshopendeepseek-flash$0.385$1.54$0.0077—1.0M—
GreenPTopendeepseek-v4.1-flash-1017$0.4022$1.6199$0.0447—1.0M—
Eden AIopentensorx/deepseek/deepseek-v4.1-flash-1017$0.5$1.5$0.125—1.0M—
Lyceumopendeepseek/deepseek-v4.1-flash$0.5$1.5$0.125—1.0M—
Requestyopendeepseek-v4.1-flash-1017$0.5$1.5$0.05—1.0M—
Requestyeuopendeepseek-v4.1-flash-1017@eu$0.5$1.5$0.05—1.0M—
Syntheticopenhf:deepseek-ai/DeepSeek-V4.1-Flash-1017$0.6$1.2$0.03—524k—
Phalaopendeepseek/deepseek-v4.1-flash-1017$0.75$1.6$0.15—1.0M—
Eden AIopenscaleway/deepseek-v4.1-flash-1017$0.6631$1.9894$0.1326—256kyesterdayout −0.3%
Scalewayopendeepseek-v4.1-flash-1017$0.672$2.016$0.134—256k—
Thinking Machinesopendeepseek-ai/DeepSeek-V4.1-Flash-1017:peft:262144$0.6$3.6$0.12—262k—
cheapllm.shopfreedeepseek-v4.1-flash-1017freefreefree—1.0M—

DeepSeek V4.1 Flash 1017 price history

Output price per 1M tokens since tracking began on Oct 18, 2026, for the 6 cheapest of 12 providers whose rate moved. Each step is a recorded change. All recent price changes.

DeepSeek V4.1 Flash 1017 output price per 1M tokens by provider, Oct 18, 2026 to Nov 16, 2026$0$0.5$1$1.5$2Oct 18, 2026Nov 2, 2026Nov 16, 2026
engy$0.12OpenRouter$0.5Prime Inference$0.7NanoGPT$0.6DevPass (LLM Gateway)$0.54Cortecs$0.609
DeepSeek V4.1 Flash 1017 price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
Eden AI$0.6649 → $0.6631$1.9946 → $1.9894−0.3%
NaNfree → $0.2948free → $1.1794—
OpenRouter$0.15 → $0.038$0.6 → $0.5−16.7%
Eden AI$0.6676 → $0.6649$2.0029 → $1.9946−0.4%
OpenRouter$0.006 → $0.15$0.5 → $0.6+20%
Eden AI$0.6728 → $0.6676$2.0185 → $2.0029−0.8%
Eden AI$0.6716 → $0.6728$2.0147 → $2.0185+0.2%
Eden AI$0.6699 → $0.6716$2.0097 → $2.0147+0.3%
Prime Inference$0.1092 → $0.0437$1.2 → $0.7−41.7%
OpenRouter$0.15 → $0.006$0.6 → $0.5−16.7%
DevPass (LLM Gateway)$0.2 → $0.135$0.8 → $0.54−32.5%
Eden AI$0.6734 → $0.6699$2.0203 → $2.0097−0.5%
EmpirioLabs AI$0.3 → $0.2$1.2 → $0.8−33.3%
Eden AI$0.676 → $0.6734$2.0281 → $2.0203−0.4%
Prime Inference$0.156 → $0.1092$1.2−30%
DevPass (LLM Gateway)$0.15 → $0.2$0.6 → $0.8+33.3%
Eden AI$0.6707 → $0.676$2.0122 → $2.0281+0.8%
Eden AI$0.6703 → $0.6707$2.011 → $2.0122+0.1%
OpenRouter$0.3 → $0.15$1.2 → $0.6−50%
Prime Inference$0.3 → $0.156$1.2−48%

Subscription plans (not per-token)

Billed per month, not per token — never counted as the cheapest offer.

Alibaba Token Planplanfreefree1.0M
Alibaba Token Plan (China)planfreefree1.0M
ClinePassplan$0.15$0.61.0M
Tencent Token Planplan$0.1501$0.60051.0M
Umans AI Coding Planplanfreefree1.0M

DeepSeek V4.1 Flash 1017 pricing FAQ

What is the cheapest DeepSeek V4.1 Flash 1017 API?

As of Nov 16, 2026, Refuseless has the lowest DeepSeek V4.1 Flash 1017 output price at $0.08 per 1M tokens, and Refuseless has the lowest input price at $0.01 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How much does DeepSeek V4.1 Flash 1017 cost on DeepSeek?

DeepSeek charges $0.15 per 1M input tokens and $0.6 per 1M output tokens for DeepSeek V4.1 Flash 1017.

How many providers offer DeepSeek V4.1 Flash 1017?

77 providers list DeepSeek V4.1 Flash 1017 on Sovyron; 89 of them sell it at a metered per-token price.

Is DeepSeek V4.1 Flash 1017 free?

One provider lists a free-tier offer: cheapllm.shop. Free tiers usually have rate limits.

Is DeepSeek V4.1 Flash 1017 included in a subscription plan?

Yes. 4 flat-rate plans include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

What is the context window of DeepSeek V4.1 Flash 1017?

DeepSeek V4.1 Flash 1017 supports a 1.1M-token context window and up to 1.1M output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves.

Estimated

—