cd /news/large-language-models/qwen3-omni-flash-realtime-deprecated · home › topics › large-language-models › article
[ARTICLE · art-153978] src=llmstatus.ai ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Qwen3-Omni Flash Realtime deprecated

Alibaba's Qwen team has marked Qwen3-Omni Flash Realtime, the qwen3-omni-flash-realtime model released 2025-09-15, as deprecated with no announced retirement date. The multimodal model handles text, image, audio and video with a 66k context window and 16k maximum output, priced at $0.52 per 1M input tokens and $1.99 per 1M output tokens. The deprecation matters for developers whose code calls the model, since no end-of-life date has been published.

read1 min views2 publishedOct 20, 2026
Qwen3-Omni Flash Realtime deprecated
Image: Llmstatus (auto-discovered)

QW◑ Deprecating

Alibaba (Qwen) · qwen3-omni-flash-realtime

Released2025-09-15

Retiresno announced date

qwentext+image+audio+video66k context16k max out$0.52 / $1.99 per 1M

also matches:

`qwen3-omni-flash-realtime`` alibaba/qwen3-omni-flash-realtime`
[provider announcement →](https://models.dev/alibaba/qwen3-omni-flash-realtime)

Does your code call Qwen3-Omni Flash Realtime?

$ curl -fsSL https://llmstatus.ai/install.sh | bash

Then mm status in any repo — it finds every model you use and flags the ones on a clock. No account, nothing uploaded.

Get alerted before it retires →

── more in #large-language-models 4 stories · sorted by recency
── more on @alibaba 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/qwen3-omni-flash-rea…] indexed:0 read:1min 2026-10-20 · —