Alibaba (Qwen)

Qwen-Omni Turbo Realtime

Generally availableProprietary33K context

Summary

Qwen-Omni Turbo Realtime is a proprietary language model from Alibaba (Qwen), released on 8 May 2025. It accepts text, images and audio and generates text and audio, with a 33K-token context window and up to 2K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.27 per million input tokens and $1.07 per million output tokens (Alibaba Cloud Model Studio), across 1 provider we track.

Qwen omni model for text, vision, audio, and multimodal agent tasks

Last verified 4 Oct 2026. Every figure on this page links to its source.

Specifications

DeveloperAlibaba (Qwen)
Release date8 May 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window33K (32,768 tokens) [models.dev]
Max output2K tokens [models.dev]
Knowledge cutoffApr 2024 [models.dev]
InputText, images and audio [models.dev]
OutputText and audio [models.dev]
Reasoning modeNo [models.dev]
Tool callingYes [models.dev]

Qwen-Omni Turbo Realtime API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Alibaba Cloud Model Studio
qwen-omni-turbo-realtime
$0.27$1.07–33Kmodels.dev, 4 Oct 2026

Frequently asked questions

What is the context window of Qwen-Omni Turbo Realtime?

Qwen-Omni Turbo Realtime has a context window of 32,768 tokens (33K) and can generate up to 2,048 tokens in a single response, according to models.dev.

How much does the Qwen-Omni Turbo Realtime API cost?

Through Alibaba Cloud Model Studio, Qwen-Omni Turbo Realtime costs $0.27 per million input tokens and $1.07 per million output tokens. Prices last verified 4 Oct 2026.

Is Qwen-Omni Turbo Realtime open source?

No. Qwen-Omni Turbo Realtime is a proprietary model; Alibaba (Qwen) has not released its weights. It is available through APIs including Alibaba Cloud Model Studio.

When was Qwen-Omni Turbo Realtime released?

Alibaba (Qwen) released Qwen-Omni Turbo Realtime on 8 May 2025, according to models.dev.

Change history

No changes detected since we started tracking this model. We re-check every source daily.

Sources