DeepSeek V3.2 Speciale

DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context proce

Creator: DeepSeek
Lifecycle: Active
Context: 163.8K
Max output: 163.8K
Released: Dec 1, 2025
Status: up

Input: $0.40 / 1M tokens
Output: $1.20 / 1M tokens
Cached read: $0.20 / 1M tokens
Cached write: — / 1M tokens
Batch discount: —%
Source: OpenRouter
Verified: Apr 5, 2026 (High)

Capabilities

Modalities: text→text
Capabilities: reasoningpromptCachingstructuredOutputs

Official Links

Intro

https://openrouter.ai/deepseek/deepseek-v3.2-speciale

Docs

https://openrouter.ai/deepseek/deepseek-v3.2-speciale

Pricing

https://openrouter.ai/models

Benchmark Coverage

Benchmark	Version	Score	Date	Source	Notes

Release History

Release	Alias	Lifecycle	Release Date	Deprecation	Shutdown	Summary
DeepSeek V3.2 Speciale	deepseek-deepseek-v3-2-speciale	Active	Dec 1, 2025	—	—	Model available via OpenRouter.

Host Coverage

Host	Type	Context	Pricing Note	Differences
OpenRouter	aggregator	163.8K	$0.40/1M in · $1.20/1M out via OpenRouter	—

Migration Guidance

Change Events

Date	Type	Title	Description	Source
Dec 1, 2025	family_added	DeepSeek V3.2 Speciale published	Model made available via OpenRouter.	OpenRouter

Other models from DeepSeek

DeepSeek Chat, DeepSeek Reasoner, DeepSeek V3, DeepSeek V3 0324, DeepSeek V3.1, DeepSeek V3.1 Terminus, DeepSeek V3.2, DeepSeek V3.2 Exp, R1, R1 0528, R1 Distill Llama 70B, R1 Distill Qwen 32B