ASR Flash is Alibaba's language model. A fast-tier automatic speech recognition model optimized for low-latency transcription.
Specifications
Canonical IDalibaba-asr-flash
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
ProviderStandard
Audio In
$ / sec
Alibaba Qwen logo
Alibaba Qwen
fun-asr-flash-2026-06-15
$0.000035

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
ASR Flash————Current
ASR Flash 8K Realtime————Available
Flash—998K$0.050$0.400Available
Flash US—1.0M——Available
MT Flash—16K$0.160$0.490Available

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
Text 4 Embedding———$0.070—
Text 3 Embedding———$0.070—
HappyHorse 1.0—————
ASR—————
ASR MTL—————
ASR MTL Realtime—————
ASR Realtime—————
Coder——1.0M$0.300$1.50
Coder PlusPlus—131K$0.502$1.00
Coder TurboTurbo—131K$0.287$0.861

Model IDs

alibaba-asr-flash
fun-asr-flash-2026-06-15