Alex Getmansemnale timpurii despre IA

DeepSeek V4 Flash

DeepSeek

LansatActualizat
Fereastră de context
1M
1.048.576 de tokeni
Intrare / Ieșire
text → text

Cronologie

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

DeepSeek V4 Flash este un model de la DeepSeek cu ponderi deschise, înregistrat pentru prima dată la data de 2026-09-20; data lansării nu este stabilită. Fereastra de context este de 1.048.576 de tokeni.

Fereastră de context
1.048.576
Intrare
text
Ieșire
text
Ponderi
Deschise

Întrebări

Care este fereastra de context a modelului DeepSeek V4 Flash?

Fereastra de context este de 1.048.576 de tokeni.

Ponderile modelului DeepSeek V4 Flash sunt disponibile public?

Da. DeepSeek publică ponderile modelului.

Când a fost lansat DeepSeek V4 Flash?

Data lansării nu este stabilită. Signal Forge l-a înregistrat pentru prima dată la data de 2026-09-20.