DeepSeek V4 Flash

Cronologia

1. 2026-04-23 · Versione dei pesi · link di riscontro

1. 2026-11-13T18:48:53.232Z · Link di riscontro · GitHub search · DeepSeek · commits · rgolde96/natively-ai-personal · @unknown
   Estratto

   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 · Link di riscontro · GitHub search · DeepSeek · commits · nikgraf/calendar · @nikgraf
3. 2026-11-13T18:48:53.232Z · Link di riscontro · GitHub search · DeepSeek · commits · miron404/lindwyrm · @miron404
   Estratto

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

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

    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 · Link di riscontro · GitHub search · DeepSeek · pulls · maximhq/bifrost · @Amit-kr26
    Estratto

    [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 · Link di riscontro · GitHub search · DeepSeek · pulls · maximhq/bifrost · @neta79
    Estratto

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

13. 2026-11-13T18:47:56.425Z · Link di riscontro · GitHub search · DeepSeek · pulls · maximhq/bifrost · @neta79
    Estratto

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

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

    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 · Link di riscontro · GitHub search · DeepSeek · pulls · SreeSharvesh/loc-arena · @ryanlail
    Estratto

    - `…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 · Link di riscontro · GitHub search · DeepSeek · pulls · Picazo333/nexova-ai-engineering · @Picazo333
    Estratto

    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 · Link di riscontro · GitHub search · DeepSeek · pulls · NixOS/nixpkgs · @asosnovsky
20. 2026-11-13T18:47:56.425Z · Link di riscontro · GitHub search · DeepSeek · pulls · NeuroLang/NeuroLang · @demianw
21. 2026-11-13T18:47:56.425Z · Link di riscontro · GitHub search · DeepSeek · pulls · NeuroLang/NeuroLang · @demianw
22. 2026-11-13T18:47:56.425Z · Link di riscontro · GitHub search · DeepSeek · pulls · I-GUIDE/iguide-ai · @ShanmukhUpad
23. 2026-11-13T18:47:56.425Z · Link di riscontro · GitHub search · DeepSeek · pulls · BerriAI/litellm · @cloudgpuapp
    Estratto

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

24. 2026-11-13T18:47:56.425Z · Link di riscontro · GitHub search · DeepSeek · pulls · 0xPlaygrounds/rig · @gold-silver-copper
25. 2026-11-05T17:52:07.101Z · Link di riscontro · DeepSeek · updates
26. 2026-08-17T07:00:00.000Z · Post di Alex · Alex Getman
    Estratto

    🚨 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 · Post di Alex · Alex Getman
    Estratto

    ⚡️ 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 · Post di Alex · Alex Getman
    Estratto

    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.