Qwen Audio 3 Plus Realtime is Alibaba's language model, starting at $0.688 / 1M input and $5.50 / 1M output. A higher-capability real-time audio model in the Qwen3 family, designed for streaming audio comprehension with improved quality over the Flash tier.
Specifications
Canonical IDalibaba-qwen-audio-3-plus-realtime
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Providers
Input ModalitiesText
Output ModalitiesText

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Alibaba Qwen logo
Alibaba Qwen
qwen-audio-3.0-realtime-plus
$0.688$5.50$0.344$2.75

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Qwen Audio 3 Plus Realtime$0.688$5.50Current
Qwen Audio 3 Plus TTSAvailable
Qwen3.7 Plus1.0M$0.320$1.28Available
Qwen3.6 Plus1.0M$0.325$1.95Available
Qwen Plus Thinking1.0M$0.260$0.780Available
Qwen VL Plus8K$0.210$0.630Available
Qwen Plus1.0M$0.115$0.287Available
Qwen3.5 Omni Plus$1.40$11.00Available

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
Qwen Audio 3 Flash RealtimeFlash$0.413$4.13
EAGLE Qwen 2.5 3B Instruct
Qwen3.7 MaxMax1.0M$1.25$3.75
Qwen3.6 27B262K$0.150$0.500
Qwen3.6 35B A3B262K$0.140$0.450
Qwen3.6 Max PreviewMax262K$1.04$6.24
Qwen3 Max ThinkingMax262K$0.780$3.90
Qwen3 MaxMax262K$0.780$3.90
Qwen3 Coder 30B A3B262K$0.150$0.600
Qwen3 Max PreviewMax262K$1.20$6.00

Model IDs

alibaba-qwen-audio-3-plus-realtime
qwen-audio-3.0-realtime-plus