Explore indexBack to Models

DeepSeek-V4-Flash

An efficiency-optimized Mixture-of-Experts (MoE) model by DeepSeek, featuring 284B total and 13B active parameters, supporting a 1M context window, and tailored for high throughput, low latency, and agentic workflows.

NEWS LOG

Related news

01DeepSeek-V4-Flash Official API Released in Public BetaDeepSeek has announced the public beta release of the official DeepSeek-V4-Flash API (DeepSeek-V4-Flash-0731). Retaining the same lightweight MoE architecture with 284B total and 13B active parameters, the re-post-trained model delivers significantly enhanced agent capabilities. Benchmark scores on Terminal Bench 2.1 and Toolathlon approach or exceed the performance of the early V4-Pro-Preview.7/31/2026