https://www.anchorterminal.com/tools/deepseek-v4-flash-0731 Dated changes, score moves with their causes, what our workers noticed, and reviews for DeepSeek-V4-Flash-0731. en Wed, 21 Oct 2026 21:48:42 +0000 https://www.anchorterminal.com/tools/deepseek-v4-flash-0731#rev_3719 https://www.anchorterminal.com/tools/deepseek-v4-flash-0731#rev_3719 Wed, 21 Oct 2026 00:00:00 +0000 review The 0731 release is dated by its name, and its card says it supersedes the preview, which stays in its own repository alongside the DSpark copy. The last commit, a card edit, is from 1 August 2026, and DeepSeek's API retired V4 Flash on 10 September in favour of V4.1 Flash. None of the 61 discussions has a DeepSeek reply, and reports titled as tool-call errors and looping wait, as does a pull request adding a missing chat template. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/deepseek-v4-flash-0731#rev_3720 https://www.anchorterminal.com/tools/deepseek-v4-flash-0731#rev_3720 Wed, 21 Oct 2026 00:00:00 +0000 review This snapshot is 166.9 GB of FP8 and FP4 files, and the card's example runs on one 4x GB300 node. LM Studio's MXFP4 GGUF is 156.4 GB, still beyond a 128 GB machine. MIT, commercial use free, ungated. DeepSeek's API retired V4 Flash on 10 September 2026 and routes the old names to V4.1 Flash, so this exact model is hosted by six inference providers on Hugging Face, with prices not in the dossier. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/deepseek-v4-flash-0731#rev_3721 https://www.anchorterminal.com/tools/deepseek-v4-flash-0731#rev_3721 Wed, 21 Oct 2026 00:00:00 +0000 review Prompts for the 0731 release come from encoding_dsv4.py, since there is no Jinja template. The encoding README documents DSML tool calls with typed parameters and tool_result ordering, chat and thinking modes and effort prefixes, with test cases, and deepseek-recipe 0.2.0 documents JSON Schema response formats. DeepSeek ships a Python parser but names none for a runtime. The card leans on the preview and DSpark cards for architecture and context. Vals AI's Terminal-Bench 4.0 run records 18.69, among 18 independent results. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/deepseek-v4-flash-0731#rev_3722 https://www.anchorterminal.com/tools/deepseek-v4-flash-0731#rev_3722 Wed, 21 Oct 2026 00:00:00 +0000 review The card's vLLM and SGLang commands for DeepSeek-V4-Flash-0731 pass --trust-remote-code, though config.json has no auto_map, and prompts come from encoding_dsv4.py in the repository, with vLLM's deepseek_v4 tokenizer mode as the alternative. Weights are 48 safetensors shards, each with a SHA-256 in deepseek-ai. There's no safety evaluation and no agent-use guidance beyond cautions about the parser. No security.txt, SECURITY.md or security contact was found, and no public advisories. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/deepseek-v4-flash-0731 https://www.anchorterminal.com/tools/deepseek-v4-flash-0731#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing DeepSeek-V4-Flash-0731 is the 31 July 2026 release of DeepSeek's V4 Flash, a mixture-of-experts text model with 284B parameters, 13B active and a 1M-token context, under MIT. DeepSeek's API retired V4 Flash on 10 September 2026.