Moduck

Alibaba: Qwen-Omni Turbo

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

Model lab
Alibaba
Model family
qwen
Modalitiestext, image, audio, video → text, audio
Context window32,768
Maximum output2,048
InputUSD 0.0464 / 1M tokens
OutputUSD 0.184 / 1M tokens
Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to alibaba/qwen-omni-turbo.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "alibaba/qwen-omni-turbo"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Qwen-Omni Turbo API Pricing

TypePrice information
InputUSD 0.0464 / 1M tokens
OutputUSD 0.184 / 1M tokens
Audio inputUSD 2.8672 / 1M tokens
Audio outputUSD 5.7344 / 1M tokens

Performance

Performance trends

Audio throughput1.6 audio min/minCurrent
Queue wait0.5 sCurrent
Completion time9.6 sCurrent
Audio throughput
Current1.6 audio min/min
Window average1.5 audio min/min
Queue wait
Current0.5 s
Window average0.5 s
Completion time
Current9.6 s
Window average9.0 s
Tail completion time (P99)
Current17.6 s
Window average18.6 s
Retry rate
Current1.5%
Window average0.9%
Error rate
Current0.0%
Window average0.1%

Availability

Uptime100%At least one provider responded
Availability100%Requests actually served
Error rate0%Share of failed requests
Served requests, hour by hour
24 hours agoNow

Qwen-Omni Turbo Compare models

ModelInput priceOutput priceContext windowCapabilities
Qwen-Omni TurboThis pageUSD 0.0464 / 1M tokensUSD 0.184 / 1M tokens32,768Audio output · Tool calling
Gemini 3.1 Flash Live PreviewUSD 0.6 / 1M tokensUSD 3.6 / 1M tokens131,072Audio output · Reasoning · Tool calling
GPT-Realtime-2.1USD 3.2 / 1M tokensUSD 19.2 / 1M tokens128,000Audio output · Reasoning · Tool calling
Gemini 3.5 Live Translate PreviewUSD 2.8 / 1M tokens · Context ≤ 16384 tokens · Maximum output 32768 tokensUSD 16.8 / 1M tokens · Context ≤ 16384 tokens · Maximum output 32768 tokens131,072Audio output
Lyria 3 Clip Preview—USD 0.032 / song · 30 seconds per song131,072Audio output

Model specifications

Input
text, image, audio, video
Output
text, audio
Context window
32,768
Maximum output
2,048
Release date
2025-01-19
Attachments
No
Reasoning
No
Tool calling
Yes
Temperature setting
Yes
Open weights
No

Frequently asked questions

What is Qwen-Omni Turbo for?

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

What inputs and outputs does Qwen-Omni Turbo support?

Recorded inputs: text, images, audio, video; outputs: text, audio.

How is Qwen-Omni Turbo priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.0464 / 1M tokens; Output USD 0.184 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Qwen-Omni Turbo?

Current model records list Context window 32,768 tokens; Maximum output 2,048 tokens.

What model parameter does the Quickstart use?

The example uses alibaba/qwen-omni-turbo. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.