Home › Drops › deepseek-ai

DeepSeek-V4-Flash-Vision-Exp deepseek-ai

Created 2026-08-31 (55 days ago) 305B MoE MIT 3 providers Model page →

Status

  1. Weights
  2. Providers
  3. Quants
  4. Pricing
  5. Articles

Weights → providers → quants → pricing → articles. A step turns on when the engine observes it; it never turns on from an announcement.

Timeline

  1. 2026-07-31 · Article: DeepSeek-V4-Flash Update source
  2. 2026-08-21 · Article: DeepSeek-v4-flash-vision-exp source
  3. 2026-08-31 · Weights published on Hugging Face source
  4. 2026-08-31 · Repo commit: initial commit source
  5. 2026-08-31 · Repo commit: Add files using upload-large-folder tool source
  6. 2026-08-31 · Repo commit: init source
  7. 2026-08-31 · Repo commit: Update README.md source
  8. 2026-08-31 · Repo commit: Update README.md source
  9. 2026-08-31 · Repo commit: Add thinking-mode encoding example and change default interactive temperature to 1.0 source
  10. 2026-08-31 · Repo commit: Update README.md source
  11. 2026-08-31 · Repo commit: Add community evaluation results for DEEP-SWE, TERMINAL-BENCH-2.1 (#5) source
  12. 2026-09-01 · Repo commit: Update Model Card for SGLang support (#12) source
  13. 2026-09-01 · Repo commit: Updata vLLM recipe (#14) source
  14. 2026-09-18 · Article: Show HN: Cactus Needle 3: 8-29MB automation models can match DeepSeek V4 Flash source
  15. 2026-10-25 · 3 hosted providers observed source
  16. 2026-10-25 · 29 community quantizations on the Hub source

Watch via RSS

Every change to DeepSeek-V4-Flash-Vision-Exp

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.