Command Palette
Search for a command to run

DeepSeek V3 0324

by Deepseek

Specifications

Input
Output
Context window
164K tokens
Released
Mar 2025

Performance

Speed
23 t/s
TTFT
758 ms
Latency
Intelligence

Pricing

Input
€0.35
per 1M tokens
Output
€1.15
per 1M tokens

About this model

Highly efficient DeepSeek flagship engineered for fast, capable reasoning and low-cost inference.

Technical specifications

Capabilities
Input modalities
Output modalities
Reasoning
No

Knowledge horizon

Released Mar 2025
Today
Since release 14 mo

See also

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