The new multimodal understanding and generation model, supporting text, image, speech, and video input as well as mixed input understanding. It can simultaneously stream text and speech, with significantly enhanced speed for multimodal content understanding. Additionally, it offers four natural dialogue tones.This model version is functionally equivalent to the snapshot model qwen-omni-turbo-2025-03-26.
Inference Service Provider
The inference service provider for qwen-omni-turbo is Alibaba Cloud Model Studio.
Model Capabilities
- China (Beijing)
- Singapore
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image Video Audio | Output Modality | Text Audio |
Model Experience | Supported | Function Calling | Unsupported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Supported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 30720 | Max Output Length | 2048 |
Context Window | 32768 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
- Singapore
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input: Text | 0.058 | Per 1M tokens |
Input: Audio | 3.584 | Per 1M tokens |
Input: Vision | 0.216 | Per 1M tokens |
Output: Text (When input contains only text) | 0.23 | Per 1M tokens |
Output: Text (When input contains images/audio/video) | 0.646 | Per 1M tokens |
Output: Text&Audio (Output text is not charged) | 7.168 | Per 1M tokens |
Input: Vision(Implicit Cache) | 0.044 | Per 1M tokens |
Input: Text(Implicit Cache) | 0.012 | Per 1M tokens |
Input: Audio(Implicit Cache) | 0.717 | Per 1M tokens |
Rate Limits
- China (Beijing)
- Singapore
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 60 |
TPM (Tokens Per Minute) | 100,000 |
Dynamic Updates
qwen-omni-turbo-latest
The new multimodal understanding and generation model, supporting text, image, speech, and video input as well as mixed input understanding. It can simultaneously stream text and speech, with significantly enhanced speed for multimodal content understanding. Additionally, it offers four natural dialogue tones. This model is a dynamically updated version.
Inference Service Provider
The inference service provider for qwen-omni-turbo-latest is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image Video Audio | Output Modality | Text Audio |
Model Experience | Supported | Function Calling | Unsupported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 30720 | Max Output Length | 2048 |
Context Window | 32768 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
- Singapore
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input: Text | 0.058 | Per 1M tokens |
Input: Audio | 3.584 | Per 1M tokens |
Input: Vision | 0.216 | Per 1M tokens |
Output: Text (When input contains only text) | 0.23 | Per 1M tokens |
Output: Text (When input contains images/audio/video) | 0.646 | Per 1M tokens |
Output: Text&Audio (Output text is not charged) | 7.168 | Per 1M tokens |
Rate Limits
- China (Beijing)
- Singapore
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 60 |
TPM (Tokens Per Minute) | 100,000 |
Snapshot Versions
qwen-omni-turbo-2025-03-26
The new multimodal understanding and generation model, supporting text, image, speech, and video input as well as mixed input understanding. It can simultaneously stream text and speech, with significantly enhanced speed for multimodal content understanding. Additionally, it offers four natural dialogue tones. This model is the snapshot from March 26, 2025, with significant improvements on visual capabilities over the snapshot of January 19, 2025.
Inference Service Provider
The inference service provider for qwen-omni-turbo-2025-03-26 is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image Video Audio | Output Modality | Text Audio |
Model Experience | Supported | Function Calling | Unsupported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 30720 | Max Output Length | 2048 |
Context Window | 32768 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
- Singapore
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input: Text | 0.058 | Per 1M tokens |
Input: Audio | 3.584 | Per 1M tokens |
Input: Vision | 0.216 | Per 1M tokens |
Output: Text (When input contains only text) | 0.23 | Per 1M tokens |
Output: Text (When input contains images/audio/video) | 0.646 | Per 1M tokens |
Output: Text&Audio (Output text is not charged) | 7.168 | Per 1M tokens |
Rate Limits
- China (Beijing)
- Singapore
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 60 |
TPM (Tokens Per Minute) | 100,000 |
qwen-omni-turbo-2025-01-19
Qwen All-Modal Understanding and Generation Large Model supports text, image, speech, video input understanding and mixed input comprehension, features simultaneous streaming generation of text and speech, significantly enhanced multi-modal content understanding speed, provides 4 natural conversational voices. This version is a snapshot from January 19, 2025, and will be maintained until approximately one month before the next snapshot release.
Inference Service Provider
The inference service provider for qwen-omni-turbo-2025-01-19 is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image Video Audio | Output Modality | Text Audio |
Model Experience | Supported | Function Calling | Unsupported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 30720 | Max Output Length | 2048 |
Context Window | 32768 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
| Billing Item | Price (USD) | Unit |
|---|---|---|
Input: Text | 0.058 | Per 1M tokens |
Input: Audio | 3.584 | Per 1M tokens |
Input: Vision | 0.216 | Per 1M tokens |
Output: Text (When input contains only text) | 0.23 | Per 1M tokens |
Output: Text (When input contains images/audio/video) | 0.646 | Per 1M tokens |
Output: Text&Audio (Output text is not charged) | 7.168 | Per 1M tokens |
Rate Limits
- China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 60 |
TPM (Tokens Per Minute) | 100,000 |