// model_detail
legacy open-weight
DeepSeek V2
by DeepSeek
Previous-generation MoE model. 236B total params. Superseded by V3.
Context window 128K 128K tokens
Max output 8K 8K tokens
Pricing /1M tok $0.14 in / $0.28 out per 1M tokens (OpenRouter)
Released May 1, 2024
// specifications
Specs & capabilities
API details
- API model ID
deepseek-v2- Internal ID
deepseek-v2- Status
- legacy
- Type
- open-weight
Capabilities
- Vision
- No
- Function calling
- 🔧 Yes
- Knowledge cutoff
- 📅 2024-05
Pricing
- Input
- $0.14 / 1M tokens
- Output
- $0.28 / 1M tokens
- Source
- OpenRouter pricing
Lifecycle
- Successor
- DeepSeek V3
// data_confidence
Data notes
⚠️ Pricing shown via OpenRouter, not first-party
// notes
Additional notes
Previous-gen MoE, 236B total params
// more_from_deepseek
More DeepSeek models
DeepSeek V3.2 Thinking active reasoning
DeepSeek V3.2 thinking mode via deepseek-reasoner endpoint. Up to 64K output with reasoning chains.
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 Superseded by V3.2 thinking.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 Superseded by V3.2 on API.
// external_links