Skip to content
Sovyron

DeepSeek V4 Pro

deepseek-pro1.1M context1.0M max outputreleased Apr 24, 2026Open weightsReasoningTool calling4 subscription plans →

As of Nov 22, 2026, the cheapest DeepSeek V4 Pro API price is $0.348 per 1M input tokens (routing.run) and $0.696 per 1M output tokens (routing.run). DeepSeek V4 Pro is offered by 72 providers in the deepseek-pro family, open weights, reasoning enabled. DeepSeek's own rate is $1.98 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
$0.348
Cheapest output
$0.696
Official (DeepSeek)
$1.98
output per 1M tokens
Providers
72
offering this model
Spread
11.1×
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 Pro API prices by provider in USD per 1M tokens, updated Nov 22, 2026
routing.runopendeepseek-v4-proCheapest$0.348Cheapest$0.696——1.0M—
EBCloudopenDeepSeek-V4-Pro$0.4286$0.8571——1.0M—
Hugging Faceopendeepseek-ai/DeepSeek-V4-Pro$0.435$0.87$0.0036—1.0M—
Modelisopendeepseek-v4-pro$0.435$0.87——1.0M—
TokenGoopendeepseek/deepseek-v4-pro$0.435$0.87——1.0M—
APIKOopendeepseek-v4-pro$0.405$1.2149$0.0135—1.0M—
Kenariopendeepseek-v4-pro$0.5714$1.14$0.0057—1.0M5d agoout −0.2%
JZSTOKENopendeepseek-v4-pro$0.4491$2.25$0.0449$0.44911.0M—
Ezkielynaopendeepseek-v4-pro$0.66$1.976$0.0219—1.0M—
CommandCodeopendeepseek/deepseek-v4-pro$0.66$1.98$0.022—1.0M—
DeepSeekopendeepseek-v4-pro$0.66$1.98$0.022—1.0M50d ago
Eden AIopendeepseek/deepseek-v4-pro$0.66$1.98$0.022—1.0M67d ago
DevPass (LLM Gateway)opendeepseek-v4-pro$0.66$1.98$0.022—1.1M23d agoout +127.6%
LLM Gatewayopendeepseek/deepseek-v4-pro$0.66$1.98$0.022—1.1M24d agoout +127.6%
LLM Gatewayopentencent/deepseek-v4-pro$0.66$1.98$0.022—1.0M23d agoout +127.6%
Ollama Cloudopendeepseek-v4-pro$0.66$1.98$0.022—1.0M—
OpenCode Goopendeepseek-v4-pro$0.66$1.98$0.022—1.0M—
OrcaRouteropendeepseek/deepseek-v4-pro$0.66$1.98$0.022—1.0M31d ago
TeamoRouteropendeepseek-v4-pro$0.66$1.98$0.022—1.0M—
ZenMuxopendeepseek/deepseek-v4-pro$0.66$1.98$0.022—1.0M31d ago
Kilo Gatewayopendeepseek/deepseek-v4-pro$0.9$1.5$0.2—1.0Myesterdayout −53.1%
OpenRouteropendeepseek/deepseek-v4-pro$0.9$1.5$0.2—1.0M8d agoout −21.5%
above.devopendeepseek-v4-pro$0.726$2.178$0.0242—1.0M—
UnoRouteropendeepseek-v4-pro$0.8999$1.7999——1.0M—
Standard Computeopendeepseek/deepseek-v4-pro$1.044$2.088$0.2088—1.0M—
AI/ML APIopendeepseek/deepseek-v4-pro$0.9$2.7$0.03—1.0M30d agoout −23.1%
ai&opendeepseek-ai/deepseek-v4-pro$1$2.5$0.25—1.0M—
Deep Infraopendeepseek-ai/DeepSeek-V4-Pro$1.3$2.6$0.1—1.0M—
LLM Gatewayopendeepinfra/deepseek-v4-pro$1.3$2.6$0.1—1.0M—
GMI Cloudopendeepseek-ai/DeepSeek-V4-Pro$1.392$2.784$0.116—1.0M—
SiliconFlowopendeepseek-ai/DeepSeek-V4-Pro$1.5016$3.135$0.135—1.0M61d ago
Zenifraopenzenifra/deepseek-v4-pro$1.5414$3.0827$0.1269—1.0M—
Aurikoopendeepseek-v4-pro$1.32$3.96$0.044—1.0M31d ago
BytePlus ModelArkopendeepseek-v4-pro-260425$1.32$3.96$0.044—1.0M—
FrogBotopendeepseek-v4-pro$1.32$3.96$0.044—128k31d ago
LLM Gatewayopenalibaba/deepseek-v4-pro$1.32$3.96$0.132—1.0M8d agoout −17.5%
LLM Gatewayopentogether-ai/deepseek-v4-pro$1.32$3.96$0.13—1.0M—
Merge Gatewayopendeepseek/deepseek-v4-pro$1.32$3.96$0.044—1.0M36d ago
Ofoxopendeepseek/deepseek-v4-pro$1.32$3.96$0.044—1.0M—
Requestyopendeepseek-v4-pro$1.32$3.96$0.044—1.0M—
SandBaseopendeepseek/deepseek-v4-pro$1.32$3.96$0.044—1.0M—
Vercel AI Gatewayopendeepseek/deepseek-v4-pro$1.32$3.96$0.132—1.0M17d agoout +100%
Novita AIopendeepseek/deepseek-v4-pro$1.6$3.2$0.135—1.0M—
CrossModelopendeepseek/deepseek-v4-pro$1.35$4.05$0.045$1.351.0M52d ago
Jalapeno CloudopenDeepSeek-V4-Pro$1.6$3.38$0.14—1.0M—
Watt CloudopenDeepSeek-V4-Pro$1.6$3.38——1.0M—
EmpirioLabs AIopendeepseek-v4-pro$1.65$3.3$1.65—1.0M—
Alibaba (China)opendeepseek-v4-pro$1.65$3.301——1.0M33d ago
SCX.aiopenDeepSeek-V4-pro$1.65$3.301$0.138—1.0M—
Venice AIopendeepseek-v4-pro$1.65$3.301$0.33—1.0M—
Cortecsopendeepseek-v4-pro$1.7$3.4$0.15—1.0M57d ago
Azureopendeepseek-v4-pro$1.74$3.48$0.145—1.0M—
Azure Cognitive Servicesopendeepseek-v4-pro$1.74$3.48$0.145—1.0M—
Cloudflare AI Gatewayopendeepseek/deepseek-v4-pro$1.74$3.48$0.145—131k—
DigitalOceanopendeepseek-v4-pro$1.74$3.48$0.348—1.0M61d ago
FastRouteropendeepseek/deepseek-v4-pro$1.74$3.48$0.145—1.0M—
HPC-AIopendeepseek/deepseek-v4-pro$1.74$3.48$0.145—1.0M—
Impossiblopendeepseek/deepseek-v4-pro$1.74$3.48$0.145—1.0M—
OpenCodeopendeepseek-v4-pro$1.74$3.48$0.145—1.0M31d ago
Vivgridopendeepseek-v4-pro$1.74$3.48$0.14—1.0M31d ago
Requestyeuopendeepseek-v4-pro@eu$1.75$3.5$0.44—1.0M—
Opperopendeepseek-v4-pro$1.7881$3.5762——1.0M—
MoarkopenDeepSeek-V4-Pro$1.8$3.6——1.0M—
RuAPIopendeepseek-v4-pro$1.584$4.752$0.06—1.0M—
DotHooshopendeepseek-v4-pro$1.694$5.082$0.0565—1.0M—
CloudCode.ONEopendeepseek-v4-pro$1.705$5.115$0.0568—1.0M—
Inference APIsopendeepseek-ai/DeepSeek-V4-Pro$1.72$5.15$0.17—1.0M—
Gisooopendeepseek-v4-pro$1.848$5.544$0.0616—1.0M—
Adzuki AIopendeepseek-v4-pro$2.5714$7.7143$0.0857—1.0M—
SenseNova (China)freedeepseek-v4-profreefreefree—1.0M—

DeepSeek V4 Pro price history

Output price per 1M tokens since tracking began on Sep 10, 2026, for the 6 cheapest of 23 providers whose rate moved. Each step is a recorded change. All recent price changes.

DeepSeek V4 Pro output price per 1M tokens by provider, Sep 10, 2026 to Nov 22, 2026$0$1.25$2.5$3.75$5Sep 10, 2026Oct 17, 2026Nov 22, 2026
Kenari$1.14DeepSeek$1.98Eden AI$1.98DevPass (LLM Gateway)$1.98LLM Gateway$1.98LLM Gateway$1.98
DeepSeek V4 Pro price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
Kilo Gateway$1.6 → $0.9$3.2 → $1.5−53.1%
Kilo Gateway$0.9 → $1.6$1.5 → $3.2+113.3%
Kilo Gateway$1.6 → $0.9$3.2 → $1.5−53.1%
Kenari$0.5714 → $0.5714$1.1429 → $1.14−0.2%
OpenRouter$0.9553 → $0.9$1.9105 → $1.5−21.5%
LLM Gateway$2.4 → $1.32$4.8 → $3.96−17.5%
OpenRouter$0.4341 → $0.9553$0.8683 → $1.9105+120%
OpenRouter$0.9483 → $0.4341$1.8966 → $0.8683−54.2%
OpenRouter$0.9553 → $0.9483$1.9105 → $1.8966−0.7%
OpenRouter$1.6 → $0.9553$3.2 → $1.9105−40.3%
Vercel AI Gateway$0.66 → $1.32$1.98 → $3.96+100%
OpenRouter$0.8162 → $1.6$1.6325 → $3.2+96%
DevPass (LLM Gateway)$0.435 → $0.66$0.87 → $1.98+127.6%
LLM Gateway$0.435 → $0.66$0.87 → $1.98+127.6%
OpenRouter$0.9553 → $0.8162$1.9105 → $1.6325−14.6%
LLM Gateway$0.435 → $0.66$0.87 → $1.98+127.6%
OpenRouter$0.2088 → $0.9553$0.4176 → $1.9105+357.5%
OpenRouter$0.5812 → $0.2088$1.1623 → $0.4176−64.1%
OpenRouter$0.9553 → $0.5812$1.9105 → $1.1623−39.2%
AI/ML API$1.17 → $0.9$3.51 → $2.7−23.1%

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$0.66$1.981.0M
SCNet Token Planplanfreefree1.0M
Volcengine Ark Coding Planplanfreefree1.0M

DeepSeek V4 Pro pricing FAQ

What is the cheapest DeepSeek V4 Pro API?

As of Nov 22, 2026, routing.run has the lowest DeepSeek V4 Pro output price at $0.696 per 1M tokens, and routing.run has the lowest input price at $0.348 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How much does DeepSeek V4 Pro cost on DeepSeek?

DeepSeek charges $0.66 per 1M input tokens and $1.98 per 1M output tokens for DeepSeek V4 Pro.

How many providers offer DeepSeek V4 Pro?

72 providers list DeepSeek V4 Pro on Sovyron; 69 of them sell it at a metered per-token price.

Is DeepSeek V4 Pro free?

One provider lists a free-tier offer: SenseNova (China). Free tiers usually have rate limits.

Is DeepSeek V4 Pro 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 Pro?

DeepSeek V4 Pro supports a 1.1M-token context window and up to 1.0M 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 and why output tokens cost more than input tokens.

Estimated

—