DeepSeek V4 Pro
DeepSeek V4 Pro 1.65T MoE flagship (0813 release) via NVIDIA NIM — 1M context, 1,000 free credits.
About the Model
Why Choose DeepSeek V4 Pro?
DeepSeek V4 Pro is the flagship 1.65T parameter MoE model engineered for autonomous agent coding, deep mathematical reasoning, and full-repository refactoring over 1M context tokens.
How to Access for Free (via NVIDIA NIM)
Why Choose DeepSeek V4 Pro on NVIDIA NIM?
Access DeepSeek's August 2026 flagship 1.65T parameter MoE model (version 0813) hosted on NVIDIA DGX Cloud. Fully accelerated for autonomous agent coding, complex mathematical reasoning, and full-repo analysis with 1M context.
Try it in your browser
Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.
Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.
Code Examples
curl https://integrate.api.nvidia.com/v1/chat/completions \
-H "Authorization: Bearer $NVIDIA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-ai/deepseek-v4-pro-0813",
"messages": [{"role": "user", "content": "Refactor this distributed Raft implementation."}]
}'
Community Feedback
Comments are tied to your GitHub account — sign in to join the discussion.