Command Palette
Search for a command to run

DeepSeek V3.1

by Deepseek

Specifications

Input
Output
Context window
164K tokens
Released
Aug 2025

Performance

Speed
21 t/s
TTFT
2.0s
Latency
Intelligence

Pricing

Input
€0.23
per 1M tokens
Output
€0.92
per 1M tokens

About this model

DeepSeek V3.1 is an optimized variant of DeepSeek V3 with enhanced chat capabilities. Offers excellent cost-efficiency with 685B MoE architecture and improved response quality for conversational tasks.

Technical specifications

Capabilities
Input modalities
Output modalities
Reasoning
Hybrid Default off

Knowledge horizon

Knowledge cutoff Oct 2025
Released Aug 2025
Today
Training to release 0 mo Since release 9 mo

See also

Add Model to Comparison
Search for a model to add
Command Palette
Search for a command to run