DeepSeek Upgrades DeepSeek-V4-Flash-0731 with Major Agentic and Coding Gains

DeepSeek published DeepSeek-V4-Flash-0731 on Hugging Face and moved the official V4-Flash API into public beta on July 31, 2026. Architecture and size unchanged from the April preview (284B MoE / 13B active, 1M context); gains come from re-post-training. Checkpoint ships with DSpark speculative decoding module attached.

API: deepseek-v4-flash now natively supports the Responses API format and is adapted for Codex. V4-Pro API and app/web models were not updated.

Pricing (DeepSeek, as reported)

  • 0.0028 cache hit, $0.28 / 1M output
  • ~1/3 of deepseek-v4-pro output pricing ($0.87)
  • 2,500 concurrency limit

Weights: MIT-licensed and ungated. Self-hosting needs substantial memory (Unsloth: ~103 GB at 3-bit / ~162 GB 8-bit; DeepSeek vLLM example on 4×GB300).

Selected vendor-reported agent benchmarks (V4-Flash-0731)

Benchmark0731Flash PreviewV4-Pro Preview
Terminal Bench 2.182.761.872.1
Toolathlon-Verified70.349.755.9
Cybergym76.738.752.7
DeepSWE54.47.312.8

Caveats: Code Agent tasks used unreleased DeepSeek Harness minimal mode; some sets internal; scores harness-sensitive.

HF model: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731