Card and pricing table agree on token billing. The general audio-generation guide still describes duration billing; the API states usage.duration is not used for token charges.
Data retention
Standard API inference prompts and responses are retained for up to 30 days, subject to legal/security exceptions; stateful files remain until deleted. The ZDR roster lists the 3.1 TTS family but does not explicitly name Next; coverage of its generated-file route requires confirmation. Eligibility is opt-in, not a default guarantee.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/tts/SpeechSynthesizer; same-region API key. Complete audio-file response.
Regions
China (Beijing). Deployment scope is not a country-only residency guarantee.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Audio generation
Input · audio generation1
$0.848
1M input tokens
Audio generation
Output · audio generation1
$1.696
1M output tokens
Rate conditions
Original Beijing list rate. Input and output charged separately. The pricing table corroborates token billing, while the general guide has a conflicting duration statement. No generic text-question quote or seconds-to-token conversion is inferred.
Standard API inference prompts and responses are retained for up to 30 days, subject to legal/security exceptions; stateful files remain until deleted. The ZDR roster lists the 3.1 TTS family but does not explicitly name Next; coverage of its generated-file route requires confirmation. Eligibility is opt-in, not a default guarantee.
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUTProcess & retain
The system processes eligible input and retains reusable state.
02 / LATER REQUESTCheck available state
Reuse depends on matching input, session state and the cache policy.
03 / CACHE HITReuse & generate
Reusing state can reduce repeated work. Any charges follow the billing rules below.
Alibaba Cloud Model Studio · China (Beijing)
qwen-audio-3.1-tts-next
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
What the measurements say
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 distinct hosted release selector, official deployment documentation and reviewed Qwen/FunAudioLLM public-weight inventories. No corresponding weights or mapping to a published checkpoint were verified. This classification applies to the hosted tier, not to the public CosyVoice or Qwen model family. Private lineage and parameter counts remain undisclosed.
