Alex GetmanAIの動きをいち早く

DeepSeek V4 Flash

DeepSeek

リリース済み更新
コンテキスト長
1M
1,048,576 トークン
入力 / 出力
テキスト → テキスト

時系列

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

DeepSeek V4 Flash は DeepSeek のAIモデルです(重み公開)。初記録:2026-09-20。リリース日は未確認です。 コンテキストウィンドウは1,048,576 トークンです。

コンテキスト長
1,048,576
入力
テキスト
出力
テキスト
重み
公開

よくある質問

DeepSeek V4 Flash のコンテキスト長は?

コンテキストウィンドウは1,048,576 トークンです。

DeepSeek V4 Flash の重みは公開されていますか?

はい。DeepSeek が重みを公開しています。

DeepSeek V4 Flash のリリース日は?

リリース日は未確認です。Signal Forge の初記録は 2026-09-20。