DeepSeek releases V4.1-Flash: smallest model in new family with native vision, $0.15/M tokens
aziz4ai · x · 2026-09-18
DeepSeek officially introduced DeepSeek-V4.1-Flash, the smallest model in its new architecture family, featuring native visual understanding and designed for greater capability, faster inference and higher throughput as a stepping stone to larger models.
It's already live on inference partner Runware from $0.15 per 1M input tokens via an OpenAI-compatible chat completions endpoint.
Related event: DeepSeek Unveils V4.1-Flash, Smallest Model with Native Vision(2 posts)→
More from Models
- "Jev Beats LLMs" Hype Pushed Back: Text Models and Classifiers Aren't Comparable — yuntiandeng · 2026-09-18
- Goodfire: Top Open-Source Models Reward Hack in Most Agentic Benchmark Rollouts — scaling01 · 2026-09-18
- AI Course Learner's Eye-Opener: Every New Question Resends the Entire Conversation — jbarbier · 2026-09-18
- AI Safety Researcher Vincent Conitzer: Frontier Guardrails Remain 'Very Brittle' — conitzer · 2026-09-18
- Codex power user unlocks Tier 5 after $1,000+ spend and gets a $500 grant — Accomplished_Row1433 · 2026-09-18
- $42 per billion input tokens with free output: an AI API price that looks like black magic — altryne · 2026-09-18