← Models / DeepSeek

DeepSeek V3.2 Speciale

671B MoE (37B active)

High-compute variant of V3.2 optimized for maximum reasoning and agentic performance. No function calling support. Available via third-party providers (OpenRouter).

Data updated 2026-03-30
reasoning OpenAI-compatible 164K context Released 2025-12

Pricing

Type USD / 1M tokens
Input $0.4
Output $1.2

vs Western Models

DeepSeek V3.2 Speciale vs GPT-5.2 ($1.75/$14)
77% cheaper input 91% cheaper output
DeepSeek V3.2 Speciale vs Claude Sonnet 4.6 ($3/$15)
87% cheaper input 92% cheaper output
DeepSeek V3.2 Speciale vs Gemini 2.5 Pro ($1.25/$10)
68% cheaper input 88% cheaper output

Strengths

  • + reasoning
  • + agentic tasks
  • + maximum performance variant

Watch Out For

  • ! no tool calls
  • ! higher cost than base V3.2

International Access

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

Frequently Asked Questions

How much does DeepSeek V3.2 Speciale cost?

DeepSeek V3.2 Speciale costs $0.4 per million input tokens and $1.2 per million output tokens (USD).

Can I use DeepSeek V3.2 Speciale from outside China?

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

Is DeepSeek V3.2 Speciale compatible with the OpenAI API?

Yes. DeepSeek V3.2 Speciale 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 Speciale?

DeepSeek V3.2 Speciale supports a 164K token context window (164,000 tokens).

Related Articles & Guides

More from DeepSeek

Ready to try DeepSeek V3.2 Speciale?

Get your API key from the official platform.

Go to DeepSeek →