Skip to content
Sovyron

DeepSeek V4 Flash 0731

deepseek-flash1.1M context1.0M max outputreleased Jul 31, 2026Open weightsReasoningTool calling3 subscription plans →

As of Nov 22, 2026, the cheapest DeepSeek V4 Flash 0731 API price is $0.0062 per 1M input tokens (JoinGonka) and $0.0185 per 1M output tokens (JoinGonka). DeepSeek V4 Flash 0731 is offered by 57 providers in the deepseek-flash family, open weights, reasoning enabled. One provider lists it as a free-tier offer. It is also included in 3 flat-rate subscription plans, Qwen (Alibaba Cloud) Token Plan Lite from $8/mo.

Cheapest input
$0.0062
Cheapest output
$0.0185
Official
—
output per 1M tokens
Providers
57
offering this model
Spread
115.7×
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 Flash 0731 API prices by provider in USD per 1M tokens, updated Nov 22, 2026
JoinGonkaopendeepseek-ai/DeepSeek-V4-Flash-0731Cheapest$0.0062Cheapest$0.0185——380k—
SAGGopendeepseek-ai/DeepSeek-V4-Flash-0731$0.0397$0.0794——400k—
engyopendeepseek-v4-flash-0731$0.045$0.09$0.009—1.0M—
NanoGPTopendeepseek/deepseek-v4-flash-0731$0.044$0.132$0.0014—1.0Myesterdayout −17.5%
NanoGPTopendeepseek/deepseek-v4-flash-0731:thinking$0.044$0.132$0.0014—1.0Myesterdayout −17.5%
Adaptionopendeepseek-v4-flash$0.0444$0.1333$0.0014—1.0M—
Boundlessopendsv4$0.04$0.21$0.02—1.0M—
Deep Infraopendeepseek-ai/DeepSeek-V4-Flash-0731$0.06$0.18$0.015—1.0M—
Eden AIopendeepinfra/deepseek-ai/DeepSeek-V4-Flash-0731$0.06$0.18$0.015—1.0M—
DevPass (LLM Gateway)opendeepseek-v4-flash-0731$0.08$0.18$0.016—1.1M11d agoout −86.4%
LLM Gatewayopendeepinfra/deepseek-v4-flash-0731$0.08$0.18$0.016—1.0M—
Kilo Gatewayopendeepseek/deepseek-v4-flash-0731$0.0443$0.3$0.035—1.0Myesterdayout −77.3%
OpenRouteropendeepseek/deepseek-v4-flash-0731$0.0443$0.3$0.035—1.0Myesterdayout +0%
Doublewordopendeepseek-ai/DeepSeek-V4-Flash-0731$0.09$0.18$0.018$0.11251.0M—
Munito AIopendeepseek-ai/deepseek-v4-flash$0.099$0.25$0.019—1.0M—
Munito AI (EU)opendeepseek-ai/deepseek-v4-flash$0.11$0.28$0.022—1.0M—
Meliousopendeepseek-v4-flash-0731$0.1115$0.2787$0.0223—1.0M24d agoout −3.8%
Basetenopendeepseek-ai/DeepSeek-V4-Flash-0731$0.13$0.26$0.028—1.0M—
Merge Gatewayopendeepseek/deepseek-v4-flash-0731$0.13$0.26$0.028—1.0M11d agoout +271.4%
Venice AIopendeepseek-v4-flash-0731$0.13$0.26$0.028—1.0M45d ago
Vercel AI Gatewayopendeepseek/deepseek-v4-flash-0731$0.13$0.26$0.028—1.0M17d agoout +69.9%
Cortecsopendeepseek-v4-flash-0731$0.082$0.413$0.06—1.0M33d ago
CoreWeaveopendeepseek-ai/DeepSeek-V4-Flash-0731$0.13$0.27$0.05—262k17d agoout −3.6%
OpenReasonopendeepseek-ai/deepseek-v4-flash-0731$0.1371$0.2743——1.0M—
DigitalOceanopendeepseek-v4-flash-0731$0.14$0.28$0.028—1.0M61d ago
Hugging Faceopendeepseek-ai/DeepSeek-V4-Flash-0731$0.14$0.28——1.0M—
LLM Gatewayopennovita/deepseek-v4-flash-0731$0.14$0.28$0.028—1.1M—
AIHubMixopendeepseek-v4-flash-0731$0.142$0.284$0.0284—1.0M—
Moarkopendeepseek-v4-flash-0731$0.15$0.3——1.0M—
Morphopenmorph-dsv4flash$0.142$0.3996$0.0359—1.0M—
Eden AIopengreenpt/deepseek-v4-flash-0731$0.1539$0.3846$0.044—1.0Myesterdayout +0.2%
GreenPTopendeepseek-v4-flash-0731$0.1596$0.399$0.0456—1.0M—
Inceptronopendeepseek-ai/DeepSeek-V4-Flash-0731$0.13$0.495$0.027free1.0M22d agoout +7.3%
Confidential AIopendeepseek-ai/DeepSeek-V4-Flash-0731$0.2$0.4$0.018—1.0M—
LLM Gatewayopentencent/deepseek-v4-flash-0731$0.15$0.6$0.003—1.0M—
Eden AIopentensorx/deepseek/deepseek-v4-flash-0731$0.25$0.3$0.0625—1.0M—
Lyceumopendeepseek/deepseek-v4-flash-0731$0.25$0.3$0.06—1.0M—
TensorXopendeepseek/deepseek-v4-flash-0731$0.25$0.3$0.06—1.0M—
Eden AIopenqwen/deepseek-v4-flash-0731$0.22$0.66$0.022—1.0M68d ago
OrcaRouteropendeepseek/deepseek-v4-flash-0731$0.22$0.66$0.007—1.0M31d ago
SiliconFlowopendeepseek-ai/DeepSeek-V4-Flash-0731$0.22$0.66$0.014—1.0M—
Tokenifyopendeepseek/deepseek-v4-flash$0.22$0.66$0.014—1.0M—
Merge Gatewayopendeepseek/deepseek-v4-flash-0731-fast$0.28$0.56$0.07—1.0M—
Requestyopendeepseek-v4-flash-0731$0.28$0.56$0.07—1.0M—
Requestyeuopendeepseek-v4-flash-0731@eu$0.28$0.56$0.07—1.0M—
Wallyopendeepseek-v4-flash-0731$0.293$0.88$0.0093—1.0M7d agoout −33.3%
Eden AIopenscaleway/deepseek-v4-flash-0731$0.4396$0.8792$0.0879—256kyesterdayout +0.2%
Scalewayopendeepseek-v4-flash-0731$0.468$0.936$0.0936—256k—
Zenifraopenzenifra/deepseek-v4-flash-0731$0.3989$1.1968$0.0526—1.0M—
EmpirioLabs AIopendeepseek-v4-flash-0731$0.424$1.272$0.424—1.0M—
Alibabaopendeepseek-v4-flash-0731$0.44$1.32$0.088—1.0M33d ago
BytePlus ModelArkopendeepseek-v4-flash-ga-260731$0.44$1.32$0.014—1.0M—
LLM Gatewayopenalibaba/deepseek-v4-flash-0731$0.44$1.32$0.044—1.0M8d agoout +230%
Novita AIopendeepseek/deepseek-v4-flash-0731$0.44$1.32$0.028—1.0M—
Ofoxopendeepseek/deepseek-v4-flash-0731$0.44$1.32$0.014—1.0M36d ago
Phalaopendeepseek/deepseek-v4-flash-0731$0.44$1.32$0.028—1.0M—
Prime Inferenceopendeepseek/deepseek-v4-flash-0731$0.44$1.32$0.014—1.0M—
Standard Computeopendeepseek/deepseek-v4-flash-0731$0.44$1.32$0.014—1.0M—
Watt CloudopenDeepSeek-V4-Flash-0731$0.44$1.32——1.0M—
Klavo AIopendeepseek/deepseek-v4-flash-0731$0.4361$1.3325$0.0848—1.0M—
Volcengine Arkopendeepseek-v4-flash-ga-260731$0.4453$1.3359$0.0148—1.0M—
Bothubopendeepseek-v4-flash-0731$0.589$1.7671——1.0M31d ago
stepping stone AGopendeepseek-ai/DeepSeek-V4-Flash-0731$0.5355$2.142$0.0803—524k—
AMDfreeDeepSeek-V4-Flashfreefreefree—1.0M—

DeepSeek V4 Flash 0731 price history

Output price per 1M tokens since tracking began on Sep 10, 2026, for the 6 cheapest of 22 providers whose rate moved. Each step is a recorded change. All recent price changes.

DeepSeek V4 Flash 0731 output price per 1M tokens by provider, Sep 10, 2026 to Nov 22, 2026$0$0.5$1$1.5$2Sep 10, 2026Oct 17, 2026Nov 22, 2026
NanoGPT$0.132NanoGPT$0.132DevPass (LLM Gateway)$0.18Kilo Gateway$0.3OpenRouter$0.3Melious$0.2787
DeepSeek V4 Flash 0731 price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
Kilo Gateway$0.44 → $0.0443$1.32 → $0.3−77.3%
NanoGPT$0.05 → $0.044$0.16 → $0.132−17.5%
NanoGPT$0.05 → $0.044$0.16 → $0.132−17.5%
Eden AI$0.1536 → $0.1539$0.3839 → $0.3846+0.2%
Eden AI$0.4387 → $0.4396$0.8774 → $0.8792+0.2%
OpenRouter$0.1 → $0.0443$0.3−55.7%
Kilo Gateway$0.047 → $0.44$0.3 → $1.32+340%
Eden AI$0.4396 → $0.4387$0.8791 → $0.8774−0.2%
Eden AI$0.1538 → $0.1536$0.3846 → $0.3839−0.2%
OpenRouter$0.047 → $0.1$0.3+112.8%
Kilo Gateway$0.44 → $0.047$1.32 → $0.3−77.3%
OpenRouter$0.06 → $0.047$0.18 → $0.3+66.7%
Eden AI$0.1542 → $0.1538$0.3855 → $0.3846−0.2%
Eden AI$0.4406 → $0.4396$0.8811 → $0.8791−0.2%
Eden AI$0.1547 → $0.1542$0.3868 → $0.3855−0.3%
Eden AI$0.4421 → $0.4406$0.8842 → $0.8811−0.3%
OpenRouter$0.0434 → $0.06$0.3 → $0.18−40%
Wally$0.44 → $0.293$1.32 → $0.88−33.3%
Eden AI$0.4432 → $0.4421$0.8865 → $0.8842−0.3%
Eden AI$0.1551 → $0.1547$0.3878 → $0.3868−0.3%

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
SCNet Token Planplanfreefree1.0M

DeepSeek V4 Flash 0731 pricing FAQ

What is the cheapest DeepSeek V4 Flash 0731 API?

As of Nov 22, 2026, JoinGonka has the lowest DeepSeek V4 Flash 0731 output price at $0.0185 per 1M tokens, and JoinGonka has the lowest input price at $0.0062 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer DeepSeek V4 Flash 0731?

57 providers list DeepSeek V4 Flash 0731 on Sovyron; 63 of them sell it at a metered per-token price.

Is DeepSeek V4 Flash 0731 free?

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

Is DeepSeek V4 Flash 0731 included in a subscription plan?

Yes. 3 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 Flash 0731?

DeepSeek V4 Flash 0731 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

—