DeepSeek opens internal beta of V4.1 Flash with native multimodal support
jiqizhixin · x · 2026-09-08
DeepSeek has started an internal beta of an intermediate V4.1 Flash version, with key upgrades including a new model architecture, native multimodal support, and stronger capabilities at higher speed and lower cost.
To try it, keep your baseurl unchanged and set the model name to deepseek-v4.1-flash-expires-on-0910. Pricing matches deepseek-v4-flash, with a rate limit of 20 concurrent requests per account. The test model expires on Sept 10.
More from Models
- Kimi K3.1 Pro tops MathArena open models, closing frontier gap to about 6 months — teortaxesTex · 2026-10-26
- Ruff creator Charlie Marsh: frontier models find infinite bugs in any software — charliermarsh · 2026-10-26
- Dev testing one skill across Opus 5.5 and Sol 6.1 finds instruction following 'all over the map' — lucasmeijer · 2026-10-26
- supermemory unveils learner-1, claiming continual learning for any model — julianweisser · 2026-10-26
- Anthropic says Opus 5.5 cuts cost per task by ~40% vs Opus 5 — taufiqintech · 2026-10-26
- AI search APIs ranked: top 12 within 7 points, yet prices differ nearly 7x — FinanceYF5 · 2026-10-26