Skip to content

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. DeepSeek V3.2 (Thinking)DeepSeekRemove
deepseek-v3.2-thinking
AttributeDeepSeek V3.2 (Thinking)deepseek-v3.2-thinking
Pricing
Input$0.19 / 1M
Output$0.275 / 1M
Cache Write (5m)$0.19 / 1M
Cache Write (1h)$0.19 / 1M
Cache Read$0.19 / 1M
Web Search$0 / 1M
Context
Max context163.8K
Max outputN/A
Capabilities
VisionYes
Function CallingYes
JSON ModeYes
StreamingYes
Catalogue
ProviderDeepSeek
Categorychat
Charge typePay As You Go
Released
Description
SummaryDeepSeek-V3.2 is an efficiency-focused large model that combines strong reasoning with reliable tool use. It introduces DeepSeek Sparse Attention to lower compute costs for long contexts while preserving quality, and uses large-scale reinforcement learning to reach GPT-5-class reasoning (including top IMO/IOI results). An agentic task-synthesis pipeline improves how it reasons with tools in interactive settings — and developers can toggle reasoning on or off as needed.