Skip to main content

Your Privacy Choices

Copyright © 2026 NVIDIA Corporation

deepseek-v4-flash Model by Deepseek-ai | NVIDIA NIM

deepseek-ai/deepseek-v4-flash

Deploy

Ready to scale? Choose your deployment path.

Partner EndpointsSelf-Hosted Deployments

Available Integrations

Deploy this model now on your endpoint provider of choice

Specifications

DeepSeek V4 Flash is a 284B MoE model with 1M-token context optimized for fast coding and agents.

MoE
agentic
coding
fast

Provider: DeepSeek AI
Last Modified: 5 months ago
Context Length: 1M
Parameters: 284B
Input Modalities: Text
Output Modalities: Text

Model Availability

Free Endpoint: Deprecated
Partner Endpoint: Available
Download Available: Available
API calls in last 30 days: 17M