DeepSeek V3.2 Thinking is DeepSeek's language model with a 128K context window and up to 8K output tokens, starting at $0.62 / 1M input and $1.85 / 1M output. The thinking-mode variant of DeepSeek V3.2, enabling extended internal reasoning traces for complex problem-solving scenarios.
Specifications
Canonical IDdeepseek-v3-2-thinking
TypeLanguage
StatusActive
CreatorDeepSeekDeepSeek
Providers
Context Window128K tokens
Max Output8K tokens
Input ModalitiesImagePDFText
Output ModalitiesText
Reasoning Effortsdefault
Release Date · 11 months ago

Capabilities

Input3/5
Text✓
Image✓
Audio·
Video·
PDF✓
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Vercel AI Gateway logo
Vercel AI Gateway
deepseek/deepseek-v3.2-thinking
$0.62$1.85

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
DeepSeek V3.2 Thinking128K$0.620$1.85Current
DeepSeek V3.2164K$0.259$0.380Deprecated
DeepSeek V3.2 Speciale164K$0.580$1.68Available
DeepSeek V3.2 Exp164K$0.270$0.410Deprecated
DeepSeek V3.2 Exp Reasoning————Available
DeepSeek V3.2 Exp————Available
DeepSeek V3.1 Terminus164K$0.270$1.00Deprecated
DeepSeek V3.1164K$0.250$0.950Deprecated
DeepSeek V3.1 671B—164K——Available
DeepSeek V3164K$0.200$0.200Deprecated
DeepSeek V3 324—164K$0.200$0.400Deprecated

Model IDs

deepseek-v3-2-thinking
deepseek/deepseek-v3.2-thinking