Skip to content
Sovyron

DeepSeek V3.2 Thinking

deepseek163k context128k max outputreleased Dec 1, 2025Open weightsReasoningTool calling

As of Nov 22, 2026, the cheapest DeepSeek V3.2 Thinking API price is $0.26 per 1M input tokens (NanoGPT) and $0.38 per 1M output tokens (NanoGPT). DeepSeek V3.2 Thinking is offered by 4 providers in the deepseek family, open weights, reasoning enabled.

Cheapest input
$0.26
Cheapest output
$0.38
Official
—
output per 1M tokens
Providers
4
offering this model
Spread
4.9×
max / min output
Free offers
0
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.

DeepSeek V3.2 Thinking API prices by provider in USD per 1M tokens, updated Nov 22, 2026
NanoGPTopendeepseek/deepseek-v3.2:thinkingCheapest$0.26Cheapest$0.38$0.13—163k8d agoout −9.1%
302.AIopendeepseek-v3.2-thinking$0.29$0.43——128k—
Kilo Gatewaydeepseek/deepseek-v3.2-thinking$0.62$1.85——128k—
Vercel AI Gatewayopendeepseek/deepseek-v3.2-thinking$0.62$1.85——128k—

DeepSeek V3.2 Thinking price history

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

DeepSeek V3.2 Thinking output price per 1M tokens by provider, Sep 10, 2026 to Nov 22, 2026$0$0.125$0.25$0.375$0.5Sep 10, 2026Oct 17, 2026Nov 22, 2026
NanoGPT$0.38
DeepSeek V3.2 Thinking price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
NanoGPT$0.286 → $0.26$0.418 → $0.38−9.1%
NanoGPT$0.2088 → $0.286$0.3096 → $0.418+35%
NanoGPT$0.28 → $0.2088$0.42 → $0.3096−26.3%

DeepSeek V3.2 Thinking pricing FAQ

What is the cheapest DeepSeek V3.2 Thinking API?

As of Nov 22, 2026, NanoGPT has the lowest DeepSeek V3.2 Thinking output price at $0.38 per 1M tokens, and NanoGPT has the lowest input price at $0.26 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer DeepSeek V3.2 Thinking?

4 providers list DeepSeek V3.2 Thinking on Sovyron; 4 of them sell it at a metered per-token price.

Is DeepSeek V3.2 Thinking free?

No provider in the Sovyron catalog lists a free tier for DeepSeek V3.2 Thinking.

What is the context window of DeepSeek V3.2 Thinking?

DeepSeek V3.2 Thinking supports a 163k-token context window and up to 128k 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

—