// model_detail
active reasoning
DeepSeek V3.2 Thinking
by DeepSeek
DeepSeek V3.2 thinking mode via deepseek-reasoner endpoint. Up to 64K output with reasoning chains.
Context window 128K 128K tokens
Max output 64K 64K tokens
Pricing /1M tok $0.28 in / $0.42 out per 1M tokens (API)
Released Mar 1, 2026
// specifications
Specs & capabilities
API details
- API model ID
deepseek-reasoner- Internal ID
deepseek-v3-2-thinking- Status
- active
- Type
- reasoning
Capabilities
- Vision
- No
- Function calling
- 🔧 Yes
- Knowledge cutoff
- 📅 2025-07
Pricing
- Input
- $0.28 / 1M tokens
- Output
- $0.42 / 1M tokens
- Source
- First-party API pricing
Lifecycle
- Predecessor
- DeepSeek R1
// notes
Additional notes
Latest DeepSeek thinking mode
// more_from_deepseek
More DeepSeek models
DeepSeek V3.2 active balanced
DeepSeek's latest model via deepseek-chat endpoint. V3.2 non-thinking mode. 128K context.
DeepSeek R1 legacy reasoning
Open-weight reasoning model. Chain-of-thought with distilled variants. Superseded by V3.2 thinking.
DeepSeek V3 legacy open-weight
Open-weight MoE model. 671B total, 37B active params. Superseded by V3.2 on API.
DeepSeek V2 legacy open-weight
Previous-generation MoE model. 236B total params. Superseded by V3.
// external_links