Alibaba ships Qwen3.8-Omni-Flash: 1M-token omni-modal input with tool calling
emmanuelvivier · x · 2026-09-18
Alibaba's Qwen team released Qwen3.8-Omni-Flash on the Qianwen AI Platform: one model that reads text, images, audio and video across a 1M-token context window, while output stays text-only — media generation and other tasks are delegated via function calling, web search and discounted cached inputs.
- The bet is on an orchestration layer, not an all-in-one generator: paired with Qwen-MM-Plugins for multimodal agent workflows and Qwen-Live Harness for continuous audiovisual interaction
- Available via Chat Completions and Responses APIs in Beijing, Singapore, Hong Kong, Tokyo, Frankfurt and Virginia
- Target use cases include meeting analysis, video editing, translation, film commentary, music-video creation and real-time conversation
- The launch announcement is still marked "draft," though production docs were updated September 18
More from coding & agent
- GitHub Actions has a lesser-known ubuntu-slim runner: 1 CPU, 5GB RAM, cheaper CI — DanielLockyer · 2026-11-02
- Before automating a workflow with AI, ask if anyone understands it end to end — djgoel123 · 2026-11-02
- One stale date silently broke a WhatsApp reply agent: 19 messages unanswered — petrusenko_max · 2026-11-02
- The 10X engineer is now just a SKILLS.md: 6 workflow rules for AI coding agents — mdancho84 · 2026-11-02
- Auditing my MCP credential broker: the worst hole was the config file — Relevant_Mousse_9117 · 2026-11-02
- AWS's open-source Strands Harness claims 45% cheaper than Claude Code, reigniting harness debate — blaizedsouza · 2026-11-02