DeepSeek Launches V4-Pro with Major Agent Upgrades and Flexible Reasoning
deepseek_ai · x · 2026-08-13
DeepSeek has officially announced the launch of the DeepSeek-V4-Pro model, focusing on significant production-level improvements for Agent capabilities.
Key updates include:
- Flexible reasoning effort: Both V4-Pro and V4-Flash allow users to adjust reasoning intensity based on task complexity (low for simple tasks, high for daily Agent workflows, max for complex scenarios).
- Native API support: Optimized compatibility with the OpenAI Responses API, featuring one-click setup specifically tailored for Codex.
V4 Pro is now accessible via the app and web through 'Expert Mode', with API model names remaining unchanged.
More from coding & agent
- holaOS: Open-source all-in-one AI agent workspace — holaboss-ai · 2026-08-13
- Obsidian Skills: Empower AI agents to use Obsidian — kepano · 2026-08-13
- HolyClaude: One-Command Deployment for a Full AI Coding Workstation — tom_doerr · 2026-08-13
- Fine-tuning Inkling-Small on Twitter Data to Clone Personal Writing Style — IgorBrigadir · 2026-08-13
- City2Graph: Open-Sourcing Python Library for Urban Heterogeneous GNNs — Tough_Ad_6598 · 2026-08-13
- Anthropic Research: Identical AI Agents Converge on Same Bad Decisions, Causing Systemic Failures — rohanpaul_ai · 2026-08-13