DeepSeek V4 Flash API Public Beta: Scores Near Opus 4.8, Natively Integrates with Codex
AI寒武纪 · wechat · 2026-07-31
DeepSeek V4 Flash official API has entered public beta. Its agent capabilities have seen a massive leap, scoring 54.4% on DeepSWE and 82.7% on TerminalBench—surpassing GLM5.2 and its own V4 Pro, and approaching Opus 4.8. Meanwhile, its pricing remains highly disruptive ($0.14/M input and $0.28/M output), seen as a strong response to OpenAI's price cuts.
Furthermore, V4 Flash now natively supports the Responses API format, allowing seamless integration with Codex. By running an official setup script or manually editing config files, users can easily configure and use DeepSeek models across Codex CLI, ChatGPT desktop, and the VSCode Codex plugin.
Related event: DeepSeek V4-Flash: Agent Leap, Open Source, Ultra-Low Price(100 posts)→
More from coding & agent
- Open-Source Tool Turns YouTube Videos into Xiaohongshu Posts with AI — yangyi · 2026-10-16
- GitHub rewrote the 800k-line Copilot runtime in Rust using AI agents, cutting CPU and memory by over 90% — bibryam · 2026-10-16
- What's the hardest part of deploying AI in real businesses that nobody talks about — djgoel123 · 2026-10-16
- DeepMind turns coding agent Antigravity into a science tool, surfacing novel antimicrobial peptide in one session — pushmeet · 2026-10-16
- Cross-review coding workflow: Claude writes the plan, Codex audits it — theteknosaur · 2026-10-16
- NPCTalk makes GTA V NPCs conversable in ~1s, open-sourced for any game — ChocolateDull8971 · 2026-10-16