Qwen3.8-Omni-Flash Realtime

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

196,608 tokensSource for Maximum input tokens (opens in a new tab)

Maximum output

65,536 tokensSource for Maximum output (opens in a new tab)

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 collected

Tool calling

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

2026-09-21Source for Release date (opens in a new tab)

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

Parameters

Not collected

Architecture

Not collected

Languages

View all 112 entries

• Chinese
• English
• German
• French
• Italian
• Czech
• Indonesian
• Thai
• Korean
• Polish
• Japanese
• Vietnamese
• Finnish
• Portuguese
• Spanish
• Dutch
• Russian
• Malay
• Catalan
• Swedish
• Turkish
• Ukrainian
• Romanian
• Slovak
• Danish
• Icelandic
• Norwegian (Bokmål)
• Macedonian
• Greek
• Hungarian
• Galician
• Filipino
• Croatian
• Bosnian
• Slovenian
• Bulgarian
• Kazakh
• Belarusian
• Latvian
• Estonian
• Azerbaijani
• Uyghur
• Swahili
• Hindi
• Esperanto
• Kyrgyz
• Tajik
• Cebuano
• Afrikaans
• Arabic
• Lithuanian
• Javanese
• Bengali
• Persian
• Hebrew
• Punjabi
• Gujarati
• Mongolian
• Asturian
• Kannada
• Marathi
• Interlingua
• Malayalam
• Maltese
• Norwegian Nynorsk
• Telugu
• Urdu
• Georgian
• Basque
• Tamil
• Odia
• Serbian
• Maori
• Northeastern Mandarin
• Guizhou dialect
• Cantonese
• Henan dialect
• Hong Kong Cantonese
• Shanghainese
• Shaanxi dialect
• Tianjin dialect
• Taiwanese Hokkien
• Yunnan dialect
• Anhui dialect
• Fujian dialect
• Gansu dialect
• Guangdong dialect
• Hubei dialect
• Hunan dialect
• Jiangxi dialect
• Shandong dialect
• Shanxi dialect
• Sichuan dialect
• Guangxi dialect
• Hainan dialect
• Chongqing dialect
• Changsha dialect
• Hangzhou dialect
• Hefei dialect
• Yinchuan dialect
• Zhengzhou dialect
• Shenyang dialect
• Wenzhou dialect
• Wuhan dialect
• Kunming dialect
• Taiyuan dialect
• Nanchang dialect
• Jinan dialect
• Lanzhou dialect
• Nanjing dialect
• Hakka
• Southern Min

Source for Languages (opens in a new tab)

Audio input languages and dialects explicitly listed in the guide: 112 named entries. The same guide advertises 113; its language subtotal is one higher than the enumerated list.

Context caching

Not collected

Data retention

Default inference prompts and responses are retained up to 30 days, subject to legal/security exceptions. Stateful conversation storage and files remain until deleted by the user. This release is not named in the current ZDR roster; do not assume zero retention.Source for Data retention (opens in a new tab)

API aliases

qwen3.8-omni-flash-realtimeSource for API aliases (opens in a new tab)

Retained audio history

Up to 100 turns and 600 cumulative secondsSource for Retained audio history (opens in a new tab)

Retained video history

Up to 50 turns and 240 cumulative secondsSource for Retained video history (opens in a new tab)

Audio channels

1, 2 or 4 over WebSocket; multichannel input uses 16 kHz PCMSource for Audio channels (opens in a new tab)

MCP tools

Remote MCP toolsSource for MCP tools (opens in a new tab)

Stock voice catalog

56 unique named presets; Tina is the defaultSource for Stock voice catalog (opens in a new tab)

Video aggregation

session.video.input.representation_compact: none by default; normal enables aggregationSource for Video aggregation (opens in a new tab)

Request mode

WebSocket, WebRTC or AOQSource for Request mode (opens in a new tab)

Usage metering

7 tokens/second input audio; 12.5 tokens/second output audio. Audio under one second is billed as one second. Spatial audio uses 2× input audio tokens for either 2 or 4 channels. Retained history is processed and counted again on subsequent turns. Spoken output bills both audio and accompanying text.Source for Usage metering (opens in a new tab)

Language coverage

Provider states 113 input languages/dialects; 112 are enumerated. Output: 36 languages/dialects.Source for Language coverage (opens in a new tab)

Speech output languages

View all 36 entries

• Chinese
• English
• German
• Italian
• Portuguese
• Spanish
• Japanese
• Korean
• French
• Russian
• Thai
• Indonesian
• Arabic
• Vietnamese
• Turkish
• Finnish
• Polish
• Hindi
• Dutch
• Czech
• Urdu
• Tagalog
• Swedish
• Danish
• Hebrew
• Icelandic
• Malay
• Norwegian
• Persian
• Sichuan dialect
• Beijing dialect
• Tianjin dialect
• Nanjing dialect
• Shaanxi dialect
• Cantonese
• Southern Min

Source for Speech output languages (opens in a new tab)

Voice cloning

SupportedSource for Voice cloning (opens in a new tab)

The enrollment target_model and conversation model must match. The published target roster lists the undated API selector; pinned-selector compatibility remains unverified.

Voice reference requirements

Mono WAV (16-bit), MP3 or M4A; at least 24 kHz; maximum 60 seconds; under 10 MB; at least 3 seconds of clear continuous speech. A 10–20 second clip is recommended.Source for Voice reference requirements (opens in a new tab)

Custom voice quota

1,000 voices per account; unused voices are deleted after one yearSource for Custom voice quota (opens in a new tab)

Voice enrollment cost

USD 0.01 per successfully created voice, separate from inference. Eligible Beijing/Singapore accounts have 1,000 creations free for 90 days; deleting a voice does not restore quota.Source for Voice enrollment cost (opens in a new tab)

Session duration

Up to 120 minutes per WebSocket session; connection closes at the limitSource for Session duration (opens in a new tab)

Search grounding

SupportedSource for Search grounding (opens in a new tab)

Tool and search restrictions

Web search and custom tool calling are mutually exclusiveSource for Tool and search restrictions (opens in a new tab)

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

Choose a voice within Qwen3.8-Omni-Flash Realtime. These are API voice identifiers, not additional model releases. Source links document each voice.

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.

Why it is included

Inference from release-specific Alibaba-managed API documentation and the reviewed official Qwen public-weight inventory. No matching weights are published for this named hosted release in that inventory. Public Qwen3.8-Flash-Next, Qwen3.8-2.4T-A95B and older Qwen-Omni checkpoints are separate identities and are excluded; this is not a blanket classification of the Qwen family.

Lifecycle dates

Sources reviewed