D
DeepSeek: deepseek-v3-0324
deepseek-v3-0324
128K context163.8K outReasoningToolsFilesCache
Released Mar 24, 2025Knowledge cutoff Sep 2025Updated Oct 29, 2026
A state-of-the-art 671B MoE model (37B active) featuring Multi-head Latent Attention (MLA) and auxiliary-loss-free load balancing. It provides a hybrid "Think/Non-think" mode, delivering SOTA performance in coding, math, and agentic tasks while remaining the most cost-efficient flagship in the 2026 market.
Mode chat
Inputs used for the providers' own purposes
At least one provider of this model uses your inputs for its own purposes, for example to train AI models. Do not enter personal data of third parties or sensitive data. You can object to this use at any time in your account settings or via "Manage consents" in the chat.
Read the privacy policyPricing
Input price
$0.24/ 1M tokens
Output price
$0.90/ 1M tokens
Context window 163.8K tokensCompatible endpoints openaiVendor DeepSeekProvider Routerah
Uptime
Performance
Loading performance data...
Usage & Ranking
Loading usage...