APIDir Signals
A source-linked change graph for AI companies, products, model families, exact models, APIs, prices, tutorials, and real external discussions.
Tracked hubs
Change intelligence
DeepSeek moved V4-Flash into public beta and documented stronger agent performance plus Responses API compatibility for Codex workflows.
DeepSeek-V4-Flash Update The official release of the DeepSeek-V4-Flash API is now in public beta. The API calling method remains unchanged — simply set the model name to deepseek-v4-flash to use the latest version. Significantly enhanced agent capabilities, with benchmark results far exceeding V4-Pro-Preview: Terminal Bench 2.1: 82.7 NL2Repo: 54.2 Cybergym: 76.7 DeepSWE: 54.4 Toolathlon verified: 70.3 Agent Last Exam: 25.2 Automation Bench (Public): 25.1 DSBench-FullStack: 68.7 DSBench-Hard: 59.6 Note 1: For the Code Agent tasks in the public benchmark sets, the official DeepSeek-V4-Flash was tested using the DeepSeek Harness minimal mode (to be released soon) as the framework, with the max effort level, topp=0.95, and temperature=1.0 Note 2: DSBench-FullStack is an internal full-stack development test set, and DSBench-Hard is an internal Coding Agent hard-problem test set The official V4-Flash natively supports the Responses API format and is specifically adapted for Codex. For the specific configuration, please refer to the documentation . DeepSeek-V4-Flash-0731 keeps the same model architecture and size as DeepSeek-V4-Flash-Preview, and was only re-post-trained. Note: This upd
DeepSeek-V4 The DeepSeek API now supports V4-Pro and V4-Flash, available via both the OpenAI ChatCompletions interface and the Anthropic interface. To access the new models, the base_url remains unchanged, and the model parameter should be set to deepseek-v4-pro or deepseek-v4-flash . The two legacy API model names, deepseek-chat and deepseek-reasoner , will be discontinued in three months (2026-07-24). During the current period, these two model names point to the non-thinking mode and thinking mode of deepseek-v4-flash , respectively. For more details, please refer to this documentation .
deepseek-chat The deepseek-chat model has been upgraded to DeepSeek-V2-0517. The model has seen a significant improvement in following instructions, with the IFEval Benchmark Prompt-Level accuracy jumping from 63.9% to 77.6%. Additionally, on API end, we have optimized model ability to follow instruction filled in the ``system" part. This optimization has significantly elevated the user experience across a variety of tasks, including immersive translation, Retrieval-Augmented Generation (RAG), and more. The model's accuracy in outputting JSON format has been enhanced. In our internal test set, the JSON parsing rate increased from 78% to 85%. By introducing appropriate regular expressions, the JSON parsing rate was further improved to 97%. Previous DeepSeek API Upgrade Date: 2026-09-10 DeepSeek-V4.1-Flash Release Date: 2026-08-21 DeepSeek-V4-Flash-Vision-Exp Release Date: 2026-08-13 DeepSeek-V4-Pro Update Date: 2026-07-31 DeepSeek-V4-Flash Update Date: 2026-04-24 DeepSeek-V4 Date: 2025-12-01 DeepSeek-V3.2 DeepSeek-V3.2-Speciale Date: 2025-09-29 DeepSeek-V3.2-Exp Date: 2025-09-22 DeepSeek-V3.1-Terminus Date: 2025-08-21 DeepSeek-V3.1 Date: 2025-05-28 deepseek-reasoner Date: 2025-03-
Publication boundary
Official and first-party repository changes may publish automatically after deterministic validation. Independent sources remain draft until review. Community links are attached as discussion evidence and cannot create an indexable fact by themselves.
Read the evidence methodBuild your watchlist
Save events and hubs locally today. Confirm your email for APIDir research updates, or request team access for entity watchlists, migration alerts, API exports, and webhooks.
See Signals plansAPIDir Delta · controlled rollout
Confirm your address to join the waitlist. Editorial delivery starts only after sender, suppression, and evidence checks are active.