← Models / DeepSeek

DeepSeek V3.2 (Thinking)

671B MoE (37B active)

Same as V3.2 but with thinking/reasoning mode enabled via deepseek-reasoner endpoint.

Data updated 2026-03-30
reasoning OpenAI-compatible Function calling 128K context Released 2025-12

Pricing

Type USD / 1M tokens CNY / 1M tokens
Input $0.28 ¥2
Output $0.42 ¥8
Cached Input $0.028 ¥0.5

vs Western Models

DeepSeek V3.2 (Thinking) vs GPT-5.2 ($1.75/$14)
84% cheaper input 97% cheaper output
DeepSeek V3.2 (Thinking) vs Claude Sonnet 4.6 ($3/$15)
91% cheaper input 97% cheaper output
DeepSeek V3.2 (Thinking) vs Gemini 2.5 Pro ($1.25/$10)
78% cheaper input 96% cheaper output

IDE Setup

Cursor

base_url: https://api.deepseek.com/v1
model: deepseek-reasoner

Cline

base_url: https://api.deepseek.com/v1
model: deepseek-reasoner

Strengths

  • + reasoning
  • + coding
  • + math

Watch Out For

  • ! content censorship
  • ! higher output token usage due to CoT

International Access

Direct access: Yes
Latency from US: 150-300ms
Registration: email
Payment: credit card

Frequently Asked Questions

How much does DeepSeek V3.2 (Thinking) cost?

DeepSeek V3.2 (Thinking) costs $0.28 per million input tokens and $0.42 per million output tokens (USD). Cached input is $0.028/M.

Can I use DeepSeek V3.2 (Thinking) from outside China?

Yes. DeepSeek V3.2 (Thinking) is directly accessible internationally. Registration requires email. Payment via credit card.

Is DeepSeek V3.2 (Thinking) compatible with the OpenAI API?

Yes. DeepSeek V3.2 (Thinking) uses an OpenAI-compatible API. You can use any OpenAI SDK by changing the base URL to api.deepseek.com.

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

DeepSeek V3.2 (Thinking) supports a 128K token context window (128,000 tokens).

How do I use DeepSeek V3.2 (Thinking) in Cursor or Cline?

Set the base URL to https://api.deepseek.com/v1 and the model name to deepseek-reasoner. Both Cursor and Cline support OpenAI-compatible providers.

Related Articles & Guides

Guide
Chinese LLM API Authentication: Every Provider Compared
 Guide
DeepSeek Cache Hit Strategy: How to Save 75% on API Costs
 Blog
Best Chinese AI Model for Your Use Case: A Decision Framework
 Blog
Chinese LLM Pricing Deep Dive: The Real Cost of Running AI in 2026
 Blog
DeepSeek vs GPT for Coding: Benchmarks, Real Costs, and When Each Wins

More from DeepSeek

DeepSeek V3.2 DeepSeek V3.2 Speciale DeepSeek R1 DeepSeek R1 0528 DeepSeek Prover V2

Ready to try DeepSeek V3.2 (Thinking)?

Get your API key from the official platform.

Go to DeepSeek →