DeepSeek-V3.2 (Non-thinking)

by DeepSeek

DeepSeek-V3.2 (Non-thinking) is a model from DeepSeek, released on December 1, 2025. It has a 131K-token context window and can generate up to 8K output tokens. API pricing is $0.28 per 1M input tokens and $0.42 per 1M output tokens.

DeepSeek-V3.2 in non-thinking mode. A powerful language model with 685B parameters using DeepSeek Sparse Attention (DSA) for efficient long-context processing. Supports JSON output, tool calls, and chat prefix completion. This is the standard chat mode without extended reasoning.

Key specs

ProviderDeepSeek
Release date2025-12-01
Licenseopen source
Context window131K tokens
Max output8K tokens
Input price$0.28 / 1M tokens
Output price$0.42 / 1M tokens

Quick answers

What is the context window of DeepSeek-V3.2 (Non-thinking)?

DeepSeek-V3.2 (Non-thinking) has a context window of 131K tokens, with a maximum output of 8K tokens per response.

How much does DeepSeek-V3.2 (Non-thinking) cost?

DeepSeek-V3.2 (Non-thinking) costs $0.28 per 1M input tokens and $0.42 per 1M output tokens through the API.

Is DeepSeek-V3.2 (Non-thinking) open source?

Yes. DeepSeek-V3.2 (Non-thinking) is an open model released under the open source license.

When was DeepSeek-V3.2 (Non-thinking) released?

DeepSeek released DeepSeek-V3.2 (Non-thinking) on December 1, 2025.

Compare on the AI leaderboard · All AI models

More models from DeepSeek