Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Alibaba Cloud / Qwen3-Omni Flash

Qwen3-Omni Flash Realtime · September 2025

The September realtime voice and vision release, still named in current regional pricing and capability references.

Language models (LLMs)Speech & voice
availableClosed weightsGeneral purposeVoice conversationVisionAudio understanding
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
17 of 27 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingSee ratesAlibaba Model Studio · Singapore
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Input modalities
Text, Image, Audio, VideoSource for Input modalities (opens in a new tab)
Output modalities
Text, AudioSource for Output modalities (opens in a new tab)
Reasoning
Not supportedSource for Reasoning (opens in a new tab)
Tool calling
Not supportedSource for Tool calling (opens in a new tab)
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2025-09-17Source for Release date (opens in a new tab)

Earliest reviewed regional platform release, not a date inferred from the API identifier.

Parameters
Not collected
Architecture
Mixture-of-experts Thinker–TalkerSource for Architecture (opens in a new tab)

Family architecture only. Private Flash parameter counts are not established.

Languages
Not collected
Context caching
Not collected
API aliases
qwen3-omni-flash-realtime-2025-09-15Source for API aliases (opens in a new tab)

Only this currently listed API selector is assigned to the record. Retired rolling/snapshot mappings are reviewed separately.

Request quotas
60 RPM and 100,000 TPM in Beijing and SingaporeSource for Request quotas (opens in a new tab)
Stock voice catalog
17 named presets; Cherry is the defaultSource for Stock voice catalog (opens in a new tab)
Usage metering
Audio input/output: 12.5 tokens/second, with subsecond clips billed as one second.Source for Usage metering (opens in a new tab)
Output billing
Text-only responses and media-conditioned text responses have different tariffs. For speech output, accompanying text is not charged.Source for Output billing (opens in a new tab)
Data retention
Standard inference prompts/responses may be retained for up to 30 days with legal/security exceptions; stateful records/files remain until deleted. These selectors are not listed in the reviewed zero-data-retention roster.Source for Data retention (opens in a new tab)
Search grounding
Not supportedSource for Search grounding (opens in a new tab)
Request mode
Realtime API over WebSocketSource for Request mode (opens in a new tab)
Speech output languages
View all 18 entries
  • Chinese
  • English
  • French
  • German
  • Russian
  • Italian
  • Spanish
  • Portuguese
  • Japanese
  • Korean
  • Shanghainese
  • Beijing dialect
  • Sichuan dialect
  • Nanjing dialect
  • Shaanxi dialect
  • Southern Min
  • Tianjin dialect
  • Cantonese
Source for Speech output languages (opens in a new tab)

Union of languages/dialects explicitly listed for the 17 current presets, not a general speech-recognition roster.

Image token calculation
One token per 32×32 pixels after resizing; 4–1,280 tokens per imageSource for Image token calculation (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.

Alibaba Model Studio · Singapore

Provider source (opens in a new tab)
API model ID
qwen3-omni-flash-realtime-2025-09-15
Access
wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime?model=qwen3-omni-flash-realtime-2025-09-15. Use a matching regional workspace API key.
Regions
Singapore
Streaming
SupportedSource for Streaming (opens in a new tab)
Reasoning
Not supportedSource for Reasoning (opens in a new tab)
Request quotas
60 RPM; 100,000 TPMSource for Request quotas (opens in a new tab)
Tool calling
Not supportedSource for Tool calling (opens in a new tab)
Search grounding
Not supportedSource for Search grounding (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Realtime multimodalInput: Audio1$4.571M tokens
Realtime multimodalOutput: Text&Audio (Output text is not charged)1$18.131M tokens
Realtime multimodalInput: Text1$0.521M tokens
Realtime multimodalOutput: Text (When input contains only text)1$1.991M tokens
Realtime multimodalInput: Vision1$0.941M tokens
Realtime multimodalOutput: Text (When input contains images/audio/video)1$3.671M tokens

Rate conditions

  1. USD per million tokens; visual and audio input are separate charges. Text-only responses use a different output rate from responses to media input. Speech output bills audio only, not accompanying text. Realtime conversation can re-bill retained input history.
Pricing source (opens in a new tab)

Data & enterprise terms

Standard inference prompts/responses may be retained for up to 30 days with legal/security exceptions; stateful records/files remain until deleted. These selectors are not listed in the reviewed zero-data-retention roster.

Read the service policy (opens in a new tab)

Alibaba Model Studio · China (Beijing)

Provider source (opens in a new tab)
API model ID
qwen3-omni-flash-realtime-2025-09-15
Access
wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/realtime?model=qwen3-omni-flash-realtime-2025-09-15. Use a matching regional workspace API key.
Regions
China (Beijing)
Streaming
SupportedSource for Streaming (opens in a new tab)
Reasoning
Not supportedSource for Reasoning (opens in a new tab)
Request quotas
60 RPM; 100,000 TPMSource for Request quotas (opens in a new tab)
Tool calling
Not supportedSource for Tool calling (opens in a new tab)
Search grounding
Not supportedSource for Search grounding (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Realtime multimodalInput: Audio1$2.7091M tokens
Realtime multimodalOutput: Text&Audio (Output text is not charged)1$10.7661M tokens
Realtime multimodalInput: Text1$0.3151M tokens
Realtime multimodalOutput: Text (When input contains only text)1$1.191M tokens
Realtime multimodalInput: Vision1$0.5591M tokens
Realtime multimodalOutput: Text (When input contains images/audio/video)1$2.1791M tokens

Rate conditions

  1. USD per million tokens; visual and audio input are separate charges. Text-only responses use a different output rate from responses to media input. Speech output bills audio only, not accompanying text. Realtime conversation can re-bill retained input history.
Pricing source (opens in a new tab)

Data & enterprise terms

Standard inference prompts/responses may be retained for up to 30 days with legal/security exceptions; stateful records/files remain until deleted. These selectors are not listed in the reviewed zero-data-retention roster.

Read the service policy (opens in a new tab)

Caching

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 Model Studio · Singapore

qwen3-omni-flash-realtime-2025-09-15
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

Alibaba Model Studio · China (Beijing)

qwen3-omni-flash-realtime-2025-09-15
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

Voice choices

17 voices

Choose a voice within Qwen3-Omni Flash Realtime · September 2025. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
CherryCherryChinese, English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, KoreanProvider preset voice. Language availability is listed for each voice.Voice source (opens in a new tab)
EthanEthanChinese, English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, KoreanProvider preset voice. Language availability is listed for each voice.Voice source (opens in a new tab)
NofishNofishChinese, English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, KoreanProvider preset voice. Language availability is listed for each voice.Voice source (opens in a new tab)
JenniferJenniferChinese, English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, KoreanProvider preset voice. Language availability is listed for each voice.Voice source (opens in a new tab)
RyanRyanChinese, English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, KoreanProvider preset voice. Language availability is listed for each voice.Voice source (opens in a new tab)
KaterinaKaterinaChinese, English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, KoreanProvider preset voice. Language availability is listed for each voice.Voice source (opens in a new tab)
EliasEliasChinese, English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, KoreanProvider preset voice. Language availability is listed for each voice.Voice source (opens in a new tab)
Shanghai - JadaJadaShanghainese, English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, Korean
Shanghai		Provider preset voice. Language availability is listed for each voice.Voice source (opens in a new tab)

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 authors explicitly distinguishing their in-house Flash variants from the public Qwen3-Omni-30B-A3B checkpoints, checked against the official Qwen weight inventory and exact API listings. Public checkpoint parameter counts, licenses and benchmark results are not assigned to this hosted release.

Classification evidence (opens in a new tab)

Lifecycle dates

Platform release · Singapore17 Sept 2025Source (opens in a new tab)
Platform release · China (Beijing)17 Sept 2025Source (opens in a new tab)

Sources reviewed