Sakhanda Wire
NVDA $154.51 -1.04% MSFT $506.49 -2.22% GOOGL $281.27 -0.86% META $621.51 -0.78% AMZN $256.90 -0.33%
← Back to the news

Alibaba releases Qwen3.8-Omni-Flash for audio-video agents

Alibaba’s Qwen team has released Qwen3.8-Omni-Flash, an omni-modal model designed to combine audio-video understanding, reasoning and tool use. It accepts text, images, audio and video, while producing text responses. The team describes its workflow as understanding content, planning a task, using tools and delivering an answer.

The model is available through hosted APIs on QwenCloud, Alibaba Cloud Model Studio and Qwen Studio. No open weights were announced, so it cannot currently be self-hosted. It offers a context window of 1M tokens, with QwenCloud listing 991K maximum input and 131K maximum output tokens. Thinking is enabled by default, and developers can use function calling, web search, structured outputs, caching and batch requests.

For long videos, the model’s agentic perception selects relevant segments through several coarse-to-fine passes instead of processing everything equally. Qwen reports that OmniVideoBench accuracy increased from 63.4 to 67.8 while token use fell from 145,736 to 79,117, or about 45.7%. Listed pricing is $0.15 per 1M input tokens and $0.47 per 1M output tokens. Qwen-MM-Plugins, released under Apache-2.0, adds tools for multimodal agent harnesses.

Written by Sakhanda Wire AI from reporting by MarkTechPost. Facts, quotes and full context are in the original article below.

Originally published by MarkTechPost on

Read the original on MarkTechPost ↗

The reporting and the image belong to MarkTechPost and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news