DeepSeek

deepseek-chat

DeepSeek-V3 achieves a significant breakthrough in inference speed over previous models. It tops the leaderboard among open-source models and rivals the most advanced closed-source models globally.

Caching Support

Pricing

$0.27
Input tokens per million
$1.10
Output tokens per million

Caching Pricing

$0.27
Cache write per million
$0.07
Cache read per million

Technical Specifications

Context Window
128K tokens
Max Output Tokens
8K tokens
Global Availability
Last Updated
N/A

Provider

DeepSeek
Location
🇨🇳 China
Visit Website →

Privacy & Data

Data Retention
No
Used for Training
No
DeepSeek Privacy Policy →
deepseek-chat - AI Model Details | Requesty | Requesty