← Models / DeepSeek

DeepSeek V3.2

671B MoE (37B active)

Current default model behind deepseek-chat API endpoint. Non-thinking mode.

chat 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 vs GPT-5.2 ($1.75/$14)
84% cheaper input 97% cheaper output
DeepSeek V3.2 vs Claude Sonnet 4.6 ($3/$15)
91% cheaper input 97% cheaper output
DeepSeek V3.2 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-chat

Cline

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

Strengths

  • + coding
  • + math
  • + cost-effective

Watch Out For

  • ! content censorship
  • ! occasional rate limits

International Access

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

More from DeepSeek

DeepSeek V3.2 (Thinking) DeepSeek V3.2 Speciale DeepSeek R1 DeepSeek R1 0528 DeepSeek Prover V2

Ready to try DeepSeek V3.2?

Get your API key from the official platform.

Go to DeepSeek →