---
id: "nr-qwen-launches-qwen3-8-omni-flash-an-omnimodal-model-3ec6bb"
slug: "qwen-launches-qwen3-8-omni-flash-an-omnimodal-model-3ec6bb"
title: "Qwen launches Qwen3.8-Omni-Flash, an omnimodal model built for agentic tasks"
observed_at: "2026-09-18T13:40:45.45798+00:00"
record_date: "2026-09-18"
date_kind: "observed_at"
novelty: "new"
source_platform: "qwen.ai"
topics: ["multimodal","ai-agents","new-models"]
entities: ["Qwen","Qwen3.8-Omni-Flash","Qwen-Live Harness"]
related_patterns: []
source_url: "https://qwen.ai/blog?id=qwen3.8-omni-flash"
source_urls: ["https://qwen.ai/blog?id=qwen3.8-omni-flash"]
basket: {"id":"0325e6b8-f527-4f9b-bfa3-3f30e57f380b","revision":1,"cluster_id":"3ec6bb63-848c-4c0c-9d11-00c2eb809077"}
type: "raw_signal"
description: "The Qwen team released Qwen3.8-Omni-Flash, an omnimodal model with a 1M-token context aimed at audio and video agent workflows."
why_it_matters: "On OmniVideoBench, an agentic mode that chooses which segments to watch raised accuracy from 63.4 to 67.8 while cutting tokens per query by about 45.7%. The team also open-sourced Qwen-Live Harness for real-time interaction. The post is marked as a draft and does not establish open model weights or independent results."
verification_level: "source-inspected"
signal_type: "newsroom_basket_signal"
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:qwen-launches-qwen3-8-omni-flash-an-omnimodal-model-3ec6bb"
retrieval_nugget: "The Qwen team released Qwen3.8-Omni-Flash, an omnimodal model with a 1M-token context aimed at audio and video agent workflows. The Qwen team launched Qwen3.8-Omni-Flash, a native omnimodal model that accepts text, image, audio, and video with a 1M-token context window, available on the Qianwen AI Platform. The team reports an average gain of more than 25% over Qwen3.5-Omni-Plus across 29"
status: "published"
visuals: []
routes: {"html":"https://newruntime.com/signals/qwen-launches-qwen3-8-omni-flash-an-omnimodal-model-3ec6bb/","markdown":"https://newruntime.com/signals/qwen-launches-qwen3-8-omni-flash-an-omnimodal-model-3ec6bb.md","json":"https://newruntime.com/signals/qwen-launches-qwen3-8-omni-flash-an-omnimodal-model-3ec6bb.json"}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
---

# Qwen launches Qwen3.8-Omni-Flash, an omnimodal model built for agentic tasks

## Retrieval answer

The Qwen team released Qwen3.8-Omni-Flash, an omnimodal model with a 1M-token context aimed at audio and video agent workflows. The Qwen team launched Qwen3.8-Omni-Flash, a native omnimodal model that accepts text, image, audio, and video with a 1M-token context window, available on the Qianwen AI Platform. The team reports an average gain of more than 25% over Qwen3.5-Omni-Plus across 29

The Qwen team launched Qwen3.8-Omni-Flash, a native omnimodal model that accepts text, image, audio, and video with a 1M-token context window, available on the Qianwen AI Platform. The team reports an average gain of more than 25% over Qwen3.5-Omni-Plus across 29 evaluations and audio input prices lower by more than 98% per hour.

On OmniVideoBench, an agentic mode that chooses which segments to watch raised accuracy from 63.4 to 67.8 while cutting tokens per query by about 45.7%. The team also open-sourced Qwen-Live Harness for real-time interaction. The post is marked as a draft and does not establish open model weights or independent results.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Multimodal](https://newruntime.com/topics/multimodal.md): Explore the multimodal topic hub.
- topic hub: [Ai Agents](https://newruntime.com/topics/ai-agents.md): Explore the ai-agents topic hub.
- topic hub: [New Models](https://newruntime.com/topics/new-models.md): Explore the new-models topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)