Standard API inference prompts and responses are retained up to 30 days, subject to legal/security exceptions; stateful files remain until deleted. The 3.1 ASR family is listed for opt-in ZDR, but asynchronous task management is explicitly excluded; this Filetrans path is not covered.Source for Data retention (opens in a new tab)
Access & pricing
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/audio/asr/transcription; asynchronous task polling. Same-region API key required.
Regions
China (Beijing). Deployment scope is not a country-only residency guarantee.
The reviewed pricing guide limits these model free quotas to Singapore.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Speech recognition
Input · speech recognition1
$0.113
1M input tokens
Speech recognition
Output · speech recognition1
$0.382
1M output tokens
Rate conditions
Original China (Beijing) list rate. Input and output have separate token charges; these are not a generic text-question tariff. Free-quota eligibility and promotional prices are separate; no currency conversion is applied.
Standard API inference prompts and responses are retained up to 30 days, subject to legal/security exceptions; stateful files remain until deleted. The 3.1 ASR family is listed for opt-in ZDR, but asynchronous task management is explicitly excluded; this Filetrans path is not covered.
POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/asr/transcription; asynchronous task polling. Same-region API key required.
Regions
Singapore / International. Deployment scope is not a country-only residency guarantee.
90-day window from the latest of account activation, model release or application approval; not a permanent free rate.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Speech recognition
Input · speech recognition1
$0.15
1M input tokens
Speech recognition
Output · speech recognition1
$0.47
1M output tokens
Rate conditions
Original Singapore list rate. Input and output have separate token charges; these are not a generic text-question tariff. Free-quota eligibility and promotional prices are separate; no currency conversion is applied.
Standard API inference prompts and responses are retained up to 30 days, subject to legal/security exceptions; stateful files remain until deleted. The 3.1 ASR family is listed for opt-in ZDR, but asynchronous task management is explicitly excluded; this Filetrans path is not covered.
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Inference from the release-specific hosted Model Studio identity, official technical/deployment documentation and reviewed Qwen/FunAudioLLM public-weight inventories. No matching weights are published in those inventories. Public Qwen-Audio, Qwen3-TTS, Qwen3-ASR, CosyVoice and Fun-ASR checkpoints have distinct names; no equivalence with this hosted selector is assumed. This is not a claim that the whole family or all Alibaba models are closed-weight.
