Skip to content
DeepSeek

DeepSeek V3.2 Exp

DeepSeek V3.2 Exp is a large language model made by DeepSeek, added to the catalog on 29 Sep 2025. It has a context window of 163,840 tokens and costs $0.27 per 1M input tokens and $0.41 per 1M output tokens. It accepts text and produces text. Typical uses: efficient long-context text analysis, research in transformer optimizations and exploring sparse attention mechanisms.

Price checked ยท source: OpenRouter

What DeepSeek V3.2 Exp is

DeepSeek V3.2 Exp, released by DeepSeek on September 29, 2025, is an experimental text-to-text model designed to explore efficient transformer architectures. It features a large context window of 163,840 tokens and introduces DeepSeek Sparse Attention (DSA) for improved efficiency in long-context scenarios. Users can control reasoning behavior with a simple boolean parameter. The model supports various parameters like frequency_penalty, max_tokens, and temperature, making it versatile for research in efficient transformer design. While it maintains performance comparable to its predecessor, V3.1, it focuses on architectural optimizations rather than raw task accuracy.

Key features

  • Experimental text-to-text model
  • DeepSeek Sparse Attention for efficiency
  • 163,840 token context window
  • Control reasoning with a boolean
  • Supports diverse parameters
  • Research-oriented design

Typical uses

  • Efficient long-context text analysis
  • Research in transformer optimizations
  • Exploring sparse attention mechanisms
  • Comparative studies with V3.1

DeepSeek V3.2 Exp pricing

US dollars, list price through OpenRouter.

Checked
DeepSeek V3.2 Exp price list
ItemStandard
Input, per 1M tokens$0.27
Output, per 1M tokens$0.41

No price change since it was added on 29 Sep 2025.

What typical tasks cost with DeepSeek V3.2 Exp
What a task costsCost
Answer a short question500 in / 300 out$0.0003
Summarise a 50-page PDF25,000 in / 800 out$0.0071
Review a 2,000-line source file30,000 in / 2,000 out$0.0089
Read a 300-page contract set150,000 in / 1,500 out$0.041
Check the provider's pageToken counts are estimates. A maker's direct price and its monthly plans can differ from the per-token price shown here.

DeepSeek V3.2 Exp specifications

DeepSeek V3.2 Exp limits and identity
Model iddeepseek/deepseek-v3.2-exp
Versiondeepseek-v3.2-exp
Context window163,840 tokensAbout 122,880 English words
Max output147,456 tokens
Knowledge cutoff2025-07-31
Added to catalog29 Sep 2025
DeepSeek V3.2 Exp capabilities
Input typestext
Output typestext
Tool callingYes
Structured outputsYes
Reasoning effort controlNo
Content moderationNot applied by provider

Sample outputs

The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.

Write a short essay

RUN20 Nov 2026
Prompt

Write 150 words on how AI might positively upend work, leisure and creativity

Output

AI promises to fundamentally reshape human existence by liberating us from routine. In work, it will automate mundane tasks, shifting our focus to strategic thinking, complex problem-solving, and empathetic roles, fostering a more fulfilling and human-centric economy. For leisure, AI will act as a hyper-personalized concierge, curating unique entertainment, travel, and learning experiences tailored to our deepest interests, making free time more enriching and adventurous. Most profoundly, in creativity, AI will serve as a collaborative partner for everyone. It will democratize artistic and intellectual expression, helping individuals compose music, write novels, or design innovations regardless of their prior training. This symbiosis won't replace human creativity but amplify it, unlocking unprecedented waves of collective imagination and personal growth.

DeepSeek V3.2 Exp questions

How much does DeepSeek V3.2 Exp cost?

DeepSeek V3.2 Exp costs $0.27 per 1M input tokens and $0.41 per 1M output tokens through OpenRouter, as checked on 22 Nov 2026. Summarising a 50-page PDF costs about $0.0071.

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

163,840 tokens, or roughly 122,880 English words. It can write up to 147,456 tokens in one response.

Can DeepSeek V3.2 Exp read images and PDFs?

No. It accepts text only. It produces text, so it cannot generate images.

How do I try DeepSeek V3.2 Exp?

Use the "Try DeepSeek V3.2 Exp" button on this page. It opens the chat with DeepSeek V3.2 Exp selected; you type the question and press send.

Try DeepSeek V3.2 Exp on your own question.

It opens in the chat with this model already selected.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.