Using DeepSeek V4 Flash on DeepSeek Platform
Implementation guide · DeepSeek V4 · DeepSeek
DeepSeek Platform exposes DeepSeek V4 Flash through model ID deepseek-v4-flash. Use the setup steps, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-10-19. Next refresh: weekly.
Quick Start
- 1
- 2Use the DeepSeek Platform SDK or REST API to call
deepseek-v4-flash— see the documentation for request format.
Code Examples
Capabilities
About DeepSeek V4 Flash
DeepSeek V4 Flash is a 284B parameter (13B activated) Mixture-of-Experts language model with 1M-token context. It uses a hybrid attention architecture combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) for long-context inference, and supports thinking and non-thinking modes. MIT licensed. The legacy API aliases deepseek-chat and deepseek-reasoner mapped to its non-thinking and thinking modes and were scheduled for discontinuation on July 24, 2026. DeepSeek retired the model from its API on September 10, 2026. The legacy model name deepseek-v4-flash is still accepted, and DeepSeek now serves those requests with DeepSeek-V4.1-Flash-1017.