Skip to main content
Explore
Models
Skills
Blueprints
GPUs
Docs
Search
⌘K
Ctrl+K
?
Forums
Support
Login
AI Models by DeepSeek AI | Try NVIDIA NIM APIs
DeepSeek AI
2 results
DeepSeek AI
Downloadable
Free Endpoint
deepseek-v4-flash
DeepSeek V4 Flash is a 284B MoE model with 1M-token context optimized for fast coding and agents.
Model
MoE
+3
coding
fast
agentic
15M
15M API calls in the last 30 days
2mo
Last updated on April 24, 2026
DeepSeek AI
Downloadable
Free Endpoint
deepseek-v4-pro
DeepSeek V4 scales to 1M-token context windows with efficient MoE architecture for coding tasks.
Model
Moe
+3
reasoning
coding
agentic
8M
8M API calls in the last 30 days
2mo
Last updated on April 24, 2026
