DeepSeek-V3.1

Open weights Active Text LLM MoE deepseek-v3-1

Hybrid thinking/non-thinking update of DeepSeek-V3 with stronger tool use and agent skills.

Released
Aug 21, 2025
Context window
131K tokens
Max output
8.2K tokens
Parameters
671B 37B active
Input price
Not disclosed
Output price
Not disclosed

Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.

Pricing

Launch priceAug 21, 2025
$0.27 in / $1.10 out
Current price
No longer sold
TierEffectiveInputOutputCached
Standard Aug 21, 2025 – Sep 5, 2025 $0.27 $1.10 $0.07
Standard Sep 5, 2025 – Sep 22, 2025 $0.56 $1.68 $0.07

Specifications

Developer
DeepSeek
Model type
Text LLM
Architecture
MoE
Parameters
671B (37B active)
Input
Text
Output
Text
Knowledge cutoff
Not disclosed
License
MIT License
API access
No first-party API
Capabilities
Agentic Long context Reasoning Tool use