Алекс Гетманранние сигналы об ИИ

DeepSeek V4 Flash

DeepSeek

РелизОбновлено
Контекстное окно
1M
1 048 576 токенов
Вход / Выход
текст → текст

Хронология

  1. · Версия весов · ссылка на источник
  1. · Ссылки на источники · GitHub search · DeepSeek · commits · rgolde96/natively-ai-personal · @unknown
    Фрагмент
    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. · Ссылки на источники · GitHub search · DeepSeek · commits · nikgraf/calendar · @nikgraf
  3. · Ссылки на источники · GitHub search · DeepSeek · commits · miron404/lindwyrm · @miron404
    Фрагмент
    defaulted to the retired deepseek-v4-flash model name.
  4. · Ссылки на источники · GitHub search · DeepSeek · commits · genji1024/dotfiles · @genji1024
  5. · Ссылки на источники · GitHub search · DeepSeek · commits · bottomless/agent-duel · @shihabcodes
  6. · Ссылки на источники · GitHub search · DeepSeek · commits · ModernNomad-98/Project-Aegis · @deepseek-v4-flash
  7. · Ссылки на источники · GitHub search · DeepSeek · commits · ModernNomad-98/Project-Aegis · @deepseek-v4-flash
  8. · Ссылки на источники · GitHub search · DeepSeek · pulls · overnightworks/speech · @dependabot[bot]
  9. · Ссылки на источники · GitHub search · DeepSeek · pulls · nikgraf/calendar · @nikgraf
  10. · Ссылки на источники · GitHub search · DeepSeek · pulls · maximhq/bifrost · @jimaldon
    Фрагмент
    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. · Ссылки на источники · GitHub search · DeepSeek · pulls · maximhq/bifrost · @Amit-kr26
    Фрагмент
    [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. · Ссылки на источники · GitHub search · DeepSeek · pulls · maximhq/bifrost · @neta79
    Фрагмент
    -d '{"model":"deepseek-v4-flash","messages":[{"role":"user","content":"Say exactly: hello world"}],"max_tokens":20}'
  13. · Ссылки на источники · GitHub search · DeepSeek · pulls · maximhq/bifrost · @neta79
    Фрагмент
    "model": "deepseek/deepseek-v4-flash",
  14. · Ссылки на источники · GitHub search · DeepSeek · pulls · gufo-org/gufo · @mduka
  15. · Ссылки на источники · GitHub search · DeepSeek · pulls · anomalyco/models.dev · @models-dev-automation[bot]
  16. · Ссылки на источники · GitHub search · DeepSeek · pulls · alibaba/rtp-llm · @fxp19950422
    Фрагмент
    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. · Ссылки на источники · GitHub search · DeepSeek · pulls · SreeSharvesh/loc-arena · @ryanlail
    Фрагмент
    - `…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. · Ссылки на источники · GitHub search · DeepSeek · pulls · Picazo333/nexova-ai-engineering · @Picazo333
    Фрагмент
    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. · Ссылки на источники · GitHub search · DeepSeek · pulls · NixOS/nixpkgs · @asosnovsky
  20. · Ссылки на источники · GitHub search · DeepSeek · pulls · NeuroLang/NeuroLang · @demianw
  21. · Ссылки на источники · GitHub search · DeepSeek · pulls · NeuroLang/NeuroLang · @demianw
  22. · Ссылки на источники · GitHub search · DeepSeek · pulls · I-GUIDE/iguide-ai · @ShanmukhUpad
  23. · Ссылки на источники · GitHub search · DeepSeek · pulls · BerriAI/litellm · @cloudgpuapp
    Фрагмент
    Usage: `litellm.completion(model="cloudgpu/deepseek-v4-flash", messages=[...])`
  24. · Ссылки на источники · GitHub search · DeepSeek · pulls · 0xPlaygrounds/rig · @gold-silver-copper
  25. · Ссылки на источники · DeepSeek · updates
  26. · Посты Алекса · Alex Getman
    Фрагмент
    🚨 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. · Посты Алекса · Alex Getman
    Фрагмент
    ⚡️ 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. · Посты Алекса · Alex Getman
    Фрагмент
    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.
Характеристики

DeepSeek V4 Flash — модель DeepSeek с открытыми весами, впервые зафиксированная 20 сент. 2026. Дата релиза не установлена. Контекстное окно — 1 048 576 токенов.

Контекстное окно
1 048 576
Вход
текст
Выход
текст
Веса
Открытые

Вопросы

Какое контекстное окно у DeepSeek V4 Flash?

Контекстное окно — 1 048 576 токенов.

Открыты ли веса DeepSeek V4 Flash?

Да. DeepSeek публикует веса модели.

Когда вышла DeepSeek V4 Flash?

Дата релиза не установлена. Signal Forge впервые зафиксировал модель 20 сент. 2026.