Alex Getmanنشانه‌های زودهنگام هوش مصنوعی

DeepSeek V4 Flash

DeepSeek

عرضه‌شدهبه‌روزشده
پنجرهٔ زمینه
1M
1٬048٬576 توکن
ورودی / خروجی
متن → متن

خط زمانی

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

DeepSeek V4 Flash مدلی از DeepSeek است و وزن‌های بازی دارد؛ نخستین‌بار در 2026-09-20 ثبت شد و تاریخ عرضهٔ آن مشخص نشده است. پنجرهٔ زمینه 1٬048٬576 توکن است.

پنجرهٔ زمینه
1٬048٬576
ورودی
متن
خروجی
متن
وزن‌ها
باز

پرسش‌ها

پنجرهٔ زمینهٔ DeepSeek V4 Flash چقدر است؟

پنجرهٔ زمینه 1٬048٬576 توکن است.

آیا وزن‌های DeepSeek V4 Flash در دسترس عموم است؟

بله. DeepSeek وزن‌ها را منتشر می‌کند.

DeepSeek V4 Flash چه زمانی عرضه شد؟

تاریخ عرضهٔ آن مشخص نشده است. Signal Forge نخستین‌بار آن را در 2026-09-20 ثبت کرد.