Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Alibaba Cloud / Qwen3.5-Omni

Qwen3.5-Omni-Plus

Multimodal analysis and conversation with text or spoken responses, regional tool support and a 262,144-token context.

Language models (LLMs)Speech & voice
availableClosed weightsGeneral purposeText generationVoice conversationVisionAudio understanding
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
35 of 37 specification fields collected
Audio durationUp to 3 hours per supplied audio fileSee specification notes below
File size limit2 GB per public URL; Base64 string below 10 MBSee specification notes below
Input / 1M tokens$1.40Alibaba Model Studio · Singapore · International
Output / 1M tokens$8.30USD · observed 14 Oct 2026

Specifications

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

Context / input limit
262,144 tokensSource for Context / input limit (opens in a new tab)
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 supportedSource for Reasoning (opens in a new tab)

The provider capability table marks Thinking mode unsupported for these exact selectors.

Tool calling
SupportedSource for Tool calling (opens in a new tab)

True means supported on at least one reviewed regional endpoint; inspect access details for restrictions.

Structured output
SupportedSource for Structured output (opens in a new tab)

True means supported on at least one reviewed regional endpoint; inspect access details for restrictions.

Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
SupportedSource for Batch processing (opens in a new tab)

True means supported on at least one reviewed regional endpoint; inspect access details for restrictions.

Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)

True means supported on at least one reviewed regional endpoint; inspect access details for restrictions.

Knowledge cutoff
Not collected
Release date
2026-03-26Source for Release date (opens in a new tab)

Earliest reviewed regional platform release, not a date inferred from a snapshot ID.

Parameters
Not collected
Architecture
Thinker–Talker with Hybrid-Attention mixture of expertsSource for Architecture (opens in a new tab)

Architecture is described for the Qwen3.5-Omni family. Private Plus/Flash parameter counts are not disclosed in the reviewed sources.

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 supportedSource for Context caching (opens in a new tab)

True means supported on at least one reviewed regional endpoint; inspect access details for restrictions.

API aliases
qwen3.5-omni-plus, qwen3.5-omni-plus-2026-03-15Source for API aliases (opens in a new tab)
Data retention
Standard inference prompts and responses are retained up to 30 days, subject to legal/security exceptions; stateful conversation storage and files remain until deleted. These Omni/LiveTranslate releases are not named in the current ZDR-supported roster.Source for Data retention (opens in a new tab)
Search grounding
SupportedSource for Search grounding (opens in a new tab)

True means supported on at least one reviewed regional endpoint; inspect access details for restrictions.

Prefix completion
Not supportedSource for Prefix completion (opens in a new tab)

True means supported on at least one reviewed regional endpoint; inspect access details for restrictions.

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

The overview still says 55 voices. The imported roster follows the current per-voice reference.

Usage metering
Input audio: 7 tokens/second; output audio: 12.5 tokens/second. Accompanying text is free when speech is generated; text-only responses are charged at the text output rate.Source for Usage metering (opens in a new tab)
Request mode
Chat Completions with streamed text or text-and-audio outputSource for Request mode (opens in a new tab)
Audio duration limits
Up to 3 hours per supplied audio fileSource for Audio duration limits (opens in a new tab)
Video duration
Up to 1 hour per supplied videoSource for Video duration (opens in a new tab)
Audio input limits
Up to 2,048 public audio URLs or 250 Base64 audio inputsSource for Audio input limits (opens in a new tab)
Maximum audio file
2 GB per public URL; Base64 string below 10 MBSource for Maximum audio file (opens in a new tab)
Source video limits
Up to 512 public video URLs or 250 Base64 inputs; 2 GB per URL; Base64 string below 10 MBSource for Source video limits (opens in a new tab)
Image input limits
Up to 20 MB per image; encoded Base64 string below 10 MBSource for Image input limits (opens in a new tab)
Batch context limit
256K tokens; audio output is unsupported in batchSource for Batch context limit (opens in a new tab)

Batch support is limited to documented regions and selectors, not every pinned snapshot.

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 · International

Provider source (opens in a new tab)
API model ID
qwen3.5-omni-plus
Access
OpenAI-compatible Chat Completions, with text-only or text-and-audio output selected in modalities. Streaming is required by the documented Omni response contract.
Regions
Singapore / International deployment scope
Tool calling
Not supportedSource for Tool calling (opens in a new tab)
Structured output
Not supportedSource for Structured output (opens in a new tab)
Search grounding
SupportedSource for Search grounding (opens in a new tab)
Prefix completion
Not supportedSource for Prefix completion (opens in a new tab)
Context caching
Not supportedSource for Context caching (opens in a new tab)
Batch processing
Not supportedSource for Batch processing (opens in a new tab)
Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)
Published request quota
60 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
100,000 tokens/minuteSource for Published token quota (opens in a new tab)
Voice cloning
SupportedSource for Voice cloning (opens in a new tab)

Undated selector is listed as an enrollment target; target_model must match the inference call.

INPUT / 1M TOKENS$1.40
OUTPUT / 1M TOKENS$8.30

Text-only input and text-only output in standard inference. Audio/image/video input, spoken output, voice enrollment and batch use separate native usage rates. Context caching is unsupported. Cached input price: not collected.

USD · observed 14 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Multimodal inferenceInput: Audio1$11.001M tokens
Multimodal inferenceOutput: Text&Audio (Output text is not charged)1$44.001M tokens
Multimodal inferenceinput:Text/Image/Video1$1.401M tokens
Multimodal inferenceOutput: Text1$8.301M tokens
Voice customizationVoice creation2$0.01successfully created voice

Rate conditions

  1. For text-and-audio responses, only audio output is billed; accompanying output text is not charged. Text-only responses use the published text output rate. Each input modality is counted separately.
  2. Separate enrollment operation, not an inference token charge. Failures are free. The documented target_model must match the conversation model; eligible regional free quotas and expiry apply.
Pricing source (opens in a new tab)Pricing source (opens in a new tab)

Data & enterprise terms

Standard inference prompts and responses are retained up to 30 days, subject to legal/security exceptions; stateful conversation storage and files remain until deleted. These Omni/LiveTranslate releases are not named in the current ZDR-supported 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
qwen3.5-omni-plus
Access
OpenAI-compatible Chat Completions, with text-only or text-and-audio output selected in modalities. Streaming is required by the documented Omni response contract.
Regions
China (Beijing)
Tool calling
SupportedSource for Tool calling (opens in a new tab)

Supported (Chat Completions, text output)

Structured output
SupportedSource for Structured output (opens in a new tab)

JSON-object mode only; strict JSON Schema support is not established.

Search grounding
SupportedSource for Search grounding (opens in a new tab)
Prefix completion
Not supportedSource for Prefix completion (opens in a new tab)
Context caching
Not supportedSource for Context caching (opens in a new tab)
Batch processing
SupportedSource for Batch processing (opens in a new tab)
Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)
Published request quota
60 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
100,000 tokens/minuteSource for Published token quota (opens in a new tab)
Voice cloning
SupportedSource for Voice cloning (opens in a new tab)

Undated selector is listed as an enrollment target; target_model must match the inference call.

INPUT / 1M TOKENS$0.96
OUTPUT / 1M TOKENS$5.50

Text-only input and text-only output in standard inference. Audio/image/video input, spoken output, voice enrollment and batch use separate native usage rates. Context caching is unsupported. Cached input price: not collected.

USD · observed 14 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Multimodal inferenceInput: Audio1$7.291M tokens
Multimodal inferenceOutput: Text&Audio (Output text is not charged)1$29.291M tokens
Multimodal inferenceinput:Text/Image/Video1$0.961M tokens
Multimodal inferenceOutput: Text1$5.501M tokens
Batch inferenceInput:Audio(Batch File)2$3.6451M tokens
Batch inferenceInput:Text/Image/Video(Batch File)2$0.481M tokens
Batch inferenceOutput:Text(Batch File)2$2.751M tokens
Batch inferenceInput:Audio(Batch Chat)2$7.291M tokens
Batch inferenceInput:Text/Image/Video(Batch Chat)2$0.961M tokens
Batch inferenceOutput:Text(Batch Chat)2$5.501M tokens
Voice customizationVoice creation3$0.01successfully created voice

Rate conditions

  1. For text-and-audio responses, only audio output is billed; accompanying output text is not charged. Text-only responses use the published text output rate. Each input modality is counted separately.
  2. Alternative batch mode, not additive to normal inference. Batch is limited to 256K context and does not support audio output. For text-and-audio responses, only audio output is billed; accompanying output text is not charged. Text-only responses use the published text output rate. Each input modality is counted separately.
  3. Separate enrollment operation, not an inference token charge. Failures are free. The documented target_model must match the conversation model; eligible regional free quotas and expiry apply.
Pricing source (opens in a new tab)Pricing source (opens in a new tab)

Data & enterprise terms

Standard inference prompts and responses are retained up to 30 days, subject to legal/security exceptions; stateful conversation storage and files remain until deleted. These Omni/LiveTranslate releases are not named in the current ZDR-supported roster.

Read the service policy (opens in a new tab)

Alibaba Model Studio · Singapore · International

Provider source (opens in a new tab)
API model ID
qwen3.5-omni-plus-2026-03-15
Access
OpenAI-compatible Chat Completions, with text-only or text-and-audio output selected in modalities. Streaming is required by the documented Omni response contract.
Regions
Singapore / International deployment scope
Tool calling
Not supportedSource for Tool calling (opens in a new tab)

The pinned card restricts tool calling to Beijing and text output.

Structured output
Not collected

Unscoped snapshot table says JSON Object, while Singapore rolling table says unsupported. Regional snapshot support is unresolved.

Search grounding
SupportedSource for Search grounding (opens in a new tab)
Prefix completion
Not supportedSource for Prefix completion (opens in a new tab)
Context caching
Not supportedSource for Context caching (opens in a new tab)
Batch processing
Not supportedSource for Batch processing (opens in a new tab)
Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)
Published request quota
60 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
100,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$1.40
OUTPUT / 1M TOKENS$8.30

Text-only input and text-only output in standard inference. Audio/image/video input, spoken output, voice enrollment and batch use separate native usage rates. Context caching is unsupported. Cached input price: not collected.

USD · observed 14 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Multimodal inferenceInput: Audio1$11.001M tokens
Multimodal inferenceOutput: Text&Audio (Output text is not charged)1$44.001M tokens
Multimodal inferenceinput:Text/Image/Video1$1.401M tokens
Multimodal inferenceOutput: Text1$8.301M tokens

Rate conditions

  1. For text-and-audio responses, only audio output is billed; accompanying output text is not charged. Text-only responses use the published text output rate. Each input modality is counted separately.
Pricing source (opens in a new tab)

Data & enterprise terms

Standard inference prompts and responses are retained up to 30 days, subject to legal/security exceptions; stateful conversation storage and files remain until deleted. These Omni/LiveTranslate releases are not named in the current ZDR-supported 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
qwen3.5-omni-plus-2026-03-15
Access
OpenAI-compatible Chat Completions, with text-only or text-and-audio output selected in modalities. Streaming is required by the documented Omni response contract.
Regions
China (Beijing)
Tool calling
SupportedSource for Tool calling (opens in a new tab)

Supported (Beijing, Chat Completions, text output)

Structured output
SupportedSource for Structured output (opens in a new tab)

JSON-object mode only; strict JSON Schema support is not established.

Search grounding
SupportedSource for Search grounding (opens in a new tab)
Prefix completion
Not supportedSource for Prefix completion (opens in a new tab)
Context caching
Not supportedSource for Context caching (opens in a new tab)
Batch processing
Not supportedSource for Batch processing (opens in a new tab)
Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)
Published request quota
60 requests/minuteSource for Published request quota (opens in a new tab)
Published token quota
100,000 tokens/minuteSource for Published token quota (opens in a new tab)
INPUT / 1M TOKENS$0.96
OUTPUT / 1M TOKENS$5.50

Text-only input and text-only output in standard inference. Audio/image/video input, spoken output, voice enrollment and batch use separate native usage rates. Context caching is unsupported. Cached input price: not collected.

USD · observed 14 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Multimodal inferenceInput: Audio1$7.291M tokens
Multimodal inferenceOutput: Text&Audio (Output text is not charged)1$29.291M tokens
Multimodal inferenceinput:Text/Image/Video1$0.961M tokens
Multimodal inferenceOutput: Text1$5.501M tokens

Rate conditions

  1. For text-and-audio responses, only audio output is billed; accompanying output text is not charged. Text-only responses use the published text output rate. Each input modality is counted separately.
Pricing source (opens in a new tab)

Data & enterprise terms

Standard inference prompts and responses are retained up to 30 days, subject to legal/security exceptions; stateful conversation storage and files remain until deleted. These Omni/LiveTranslate releases are not named in the current ZDR-supported 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.

Voice choices

56 voices

Choose a voice within Qwen3.5-Omni-Plus. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
TinaTinaChinese (Mandarin), English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, Korean, Thai, Indonesian, Arabic, Vietnamese, Turkish, Finnish, Polish, Hindi, Dutch, Czech, Urdu, Tagalog, Swedish, Danish, Hebrew, Icelandic, Malay, Norwegian, Persian
See the published language list		Provider preset voice. Availability and pronunciation vary by language.Voice source (opens in a new tab)
CindyCindyChinese (Taiwanese accent), English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, Korean, Thai, Indonesian, Arabic, Vietnamese, Turkish, Finnish, Polish, Hindi, Dutch, Czech, Urdu, Tagalog, Swedish, Danish, Hebrew, Icelandic, Malay, Norwegian, Persian
See the published language list		Provider preset voice. Availability and pronunciation vary by language.Voice source (opens in a new tab)
Liora MiraLiora MiraChinese (Mandarin), English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, Korean, Thai, Indonesian, Arabic, Vietnamese, Turkish, Finnish, Polish, Hindi, Dutch, Czech, Urdu, Tagalog, Swedish, Danish, Hebrew, Icelandic, Malay, Norwegian, Persian
See the published language list		Provider preset voice. Availability and pronunciation vary by language.Voice source (opens in a new tab)
SunnybobiSunnybobiChinese (Mandarin), English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, Korean, Thai, Indonesian, Arabic, Vietnamese, Turkish, Finnish, Polish, Hindi, Dutch, Czech, Urdu, Tagalog, Swedish, Danish, Hebrew, Icelandic, Malay, Norwegian, Persian
See the published language list		Provider preset voice. Availability and pronunciation vary by language.Voice source (opens in a new tab)
RaymondRaymondChinese (Mandarin), English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, Korean, Thai, Indonesian, Arabic, Vietnamese, Turkish, Finnish, Polish, Hindi, Dutch, Czech, Urdu, Tagalog, Swedish, Danish, Hebrew, Icelandic, Malay, Norwegian, Persian
See the published language list		Provider preset voice. Availability and pronunciation vary by language.Voice source (opens in a new tab)
EthanEthanChinese (Mandarin), English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, Korean, Thai, Indonesian, Arabic, Vietnamese, Turkish, Finnish, Polish, Hindi, Dutch, Czech, Urdu, Tagalog, Swedish, Danish, Hebrew, Icelandic, Malay, Norwegian, Persian
See the published language list		Provider preset voice. Availability and pronunciation vary by language.Voice source (opens in a new tab)
Theo CalmTheo CalmChinese (Mandarin), English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, Korean, Thai, Indonesian, Arabic, Vietnamese, Turkish, Finnish, Polish, Hindi, Dutch, Czech, Urdu, Tagalog, Swedish, Danish, Hebrew, Icelandic, Malay, Norwegian, Persian
See the published language list		Provider preset voice. Availability and pronunciation vary by language.Voice source (opens in a new tab)
SerenaSerenaChinese (Mandarin), English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, Korean, Thai, Indonesian, Arabic, Vietnamese, Turkish, Finnish, Polish, Hindi, Dutch, Czech, Urdu, Tagalog, Swedish, Danish, Hebrew, Icelandic, Malay, Norwegian, Persian
See the published language list		Provider preset voice. Availability and pronunciation vary by language.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 official API-served release and exact Model Studio cards, checked against the reviewed official Qwen public-weight inventory. No corresponding weights are published for this named release in that inventory. Public Qwen2.5-Omni and Qwen3-Omni checkpoints are excluded; their architectures and parameter counts are not treated as the hosted model identity.

Classification evidence (opens in a new tab)

Lifecycle dates

Platform release · Singapore / International26 Mar 2026Source (opens in a new tab)
Platform release · China (Beijing)30 Mar 2026Source (opens in a new tab)
Official research announcement30 Mar 2026Source (opens in a new tab)

Sources reviewed