DeepSeek V4 Flash

Cronologia

1. 2026-04-23 · Versão dos pesos · link de referência

1. 2026-11-13T18:48:53.232Z · Links de referência · GitHub search · DeepSeek · commits · rgolde96/natively-ai-personal · @unknown
   Excerto

   feat(llm): DeepSeek V4 Flash on OpenRouter with reasoning off and Fireworks/Wafer/DeepInfra order (D-30); record owner answers, WS23, owner info page

2. 2026-11-13T18:48:53.232Z · Links de referência · GitHub search · DeepSeek · commits · nikgraf/calendar · @nikgraf
3. 2026-11-13T18:48:53.232Z · Links de referência · GitHub search · DeepSeek · commits · miron404/lindwyrm · @miron404
   Excerto

   defaulted to the retired deepseek-v4-flash model name.

4. 2026-11-13T18:48:53.232Z · Links de referência · GitHub search · DeepSeek · commits · genji1024/dotfiles · @genji1024
5. 2026-11-13T18:48:53.232Z · Links de referência · GitHub search · DeepSeek · commits · bottomless/agent-duel · @shihabcodes
6. 2026-11-13T18:48:53.232Z · Links de referência · GitHub search · DeepSeek · commits · ModernNomad-98/Project-Aegis · @deepseek-v4-flash
7. 2026-11-13T18:48:53.232Z · Links de referência · GitHub search · DeepSeek · commits · ModernNomad-98/Project-Aegis · @deepseek-v4-flash
8. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · overnightworks/speech · @dependabot[bot]
9. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · nikgraf/calendar · @nikgraf
10. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · maximhq/bifrost · @jimaldon
    Excerto

    needed. The model catalog datasheet already carries `tencent/deepseek-v4-pro`, `tencent/deepseek-v4-flash` and `tencent/minimax-m3`; live-only models are listed with blank pricing and can be priced via overrides.

11. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · maximhq/bifrost · @Amit-kr26
    Excerto

    [x] Live run with a real key against `deepseek-v4-flash`: simple chat, multi-turn, streaming, tool calls (single/multiple/automatic/end-to-end), list models (incl. pagination), Responses API (incl. streaming), and

12. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · maximhq/bifrost · @neta79
    Excerto

    -d '{"model":"deepseek-v4-flash","messages":[{"role":"user","content":"Say exactly: hello world"}],"max_tokens":20}'

13. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · maximhq/bifrost · @neta79
    Excerto

    "model": "deepseek/deepseek-v4-flash",

14. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · gufo-org/gufo · @mduka
15. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · anomalyco/models.dev · @models-dev-automation[bot]
16. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · alibaba/rtp-llm · @fxp19950422
    Excerto

    Brings the DeepSeek V4 Flash PPU decode path to the execution shape measured in #1434. Every new behavior is opt-in or keeps its previous default.

17. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · SreeSharvesh/loc-arena · @ryanlail
    Excerto

    - `…control-note.glm-flash.yaml` and `…control-note.deepseek-v4-flash.yaml`: the same run with GLM 5.3 Flash and DeepSeek V4 Flash as the untrusted agent, each with its model file.

18. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · Picazo333/nexova-ai-engineering · @Picazo333
    Excerto

    Modelo de generación: `online/openrouter/deepseek/deepseek-v4-flash` en `https://llm.4geeks.ai/v1`. Embeddings: `online/openrouter/perplexity/pplx-embed-v1-0.6b`.

19. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · NixOS/nixpkgs · @asosnovsky
20. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · NeuroLang/NeuroLang · @demianw
21. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · NeuroLang/NeuroLang · @demianw
22. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · I-GUIDE/iguide-ai · @ShanmukhUpad
23. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · BerriAI/litellm · @cloudgpuapp
    Excerto

    Usage: `litellm.completion(model="cloudgpu/deepseek-v4-flash", messages=[...])`

24. 2026-11-13T18:47:56.425Z · Links de referência · GitHub search · DeepSeek · pulls · 0xPlaygrounds/rig · @gold-silver-copper
25. 2026-11-05T17:52:07.101Z · Links de referência · DeepSeek · updates
26. 2026-08-17T07:00:00.000Z · Publicações de Alex · Alex Getman
    Excerto

    🚨 DeepSeek slashed OpenCode Go limits 17x DeepSeek V4 Flash limits dropped from 63,300 to 3,800, while V4 Pro fell from 3,450 to 1,050. This comes as DeepSeek API prices have jumped sharply.

27. 2026-08-03T08:01:30.947Z · Publicações de Alex · Alex Getman
    Excerto

    ⚡️ Alibaba released Qwen 3.8 Max The new 2.4T parameter flagship benchmarks in the same league as GPT-5.6 Sol, Claude Opus 4.8 and Fable 5. API pricing is $2/M input and $6/M output, roughly half the cost of GPT-5.6 Terra and Claude Sonnet. Now it’s up to users to see whether Qwen can beat DeepSeek-V4-Flash and GPT-5.6 Luna on price to performance.

28. 2026-07-31T11:26:38.354Z · Publicações de Alex · Alex Getman
    Excerto

    Yesterday GPT 5.6 Luna pushed the Pareto frontier for intelligence and cost. Today DeepSeek V4 Flash did it again and pushed it even further.