Alibaba Cloud: Qwen3.5-Omni-Plus

Qwen3.5 Omni Plus is designed for broad multimedia understanding across text, images, sound, and video. It is useful for analyzing richer source material, such as interpreting a recording together with the scene and dialogue it contains.

Compare models

qwen3.5-omni-plus

AvailableAlibaba CloudChat

Input / Output: $1.40 / $8.30
Context: 197K
Max output: 64K
Modalities: VisionChat

About Qwen3.5-Omni-Plus

Qwen3.5-Omni-Plus is the higher-quality tier of Alibaba's Qwen3.5-Omni family. It reads text, images, audio, and video in one request and can reply in text or speech, using a thinker-talker design on a mixture-of-experts base. It is meant for richer source material, such as a recording with its scene and dialogue, where Qwen3.5-Omni-Flash may miss detail, at the cost of more compute per request.

Where it works well

Analyzes recordings that combine speech, sound, and picture rather than treating them separately.
Recognizes spoken input in 113 languages and can answer aloud in 74 languages and 39 dialects.
Accepts long media, up to roughly 3 hours of audio or 1 hour of video per request.
Offers 55 built-in voices plus custom voices for spoken replies.

When to choose another model

It costs more per request than Qwen3.5-Omni-Flash, so reserve it for the recordings where quality matters.
Replies are text or speech, so producing images or video requires a different model.
Live streaming conversation is handled by the separate Qwen3.5-Omni-Plus-Realtime model.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Text to textMessages API

POST/v1/messages

API format:

curl https://api.tokenlab.sh/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-xxx" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "qwen3.5-omni-plus",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Text Output

per 1M tokens

Official price: Input $1.40 / Output $8.30 / Text Input $1.40 / Audio Input $11.00 / Image Input $1.40 / Text Output $8.30 / Audio Output $44.00
Verified price: —
Discount: —

Audio on

per 1M tokens

Official price: Input $1.40 / Output $44.00 / Text Input $1.40 / Audio Input $11.00 / Image Input $1.40 / Text Output $0.00 / Audio Output $44.00
Verified price: —
Discount: —

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Text Output	Input $1.40 / Output $8.30 / Text Input $1.40 / Audio Input $11.00 / Image Input $1.40 / Text Output $8.30 / Audio Output $44.00	—	—
Audio on	Input $1.40 / Output $44.00 / Text Input $1.40 / Audio Input $11.00 / Image Input $1.40 / Text Output $0.00 / Audio Output $44.00	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 6:36 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Qwen3.5-Omni-Plus in Console with a prompt ready to edit or send.

Help me try qwen3.5-omni-plus with a short message at /v1/messages. Show the reply, latency, and cost.

Use cases

Best for

Vision

Interview and call analysis
Upload a long recording and ask for themes, contradictions, and quotes with their position in the audio.
Video review
Check a training or product video for what is said and shown, and flag where narration and visuals disagree.
Multilingual media archives
Transcribe and summarize mixed-language audio, including dialect speech, into a single working language for review.

Prompt examples

Review this recorded sales call and mark every point where the customer hesitated, with the timestamp and what was said.

Compare what the narrator says with what the screen shows in this tutorial and list the mismatches.

Transcribe this Sichuan-dialect recording into standard Chinese and summarize it in English.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

When should I choose Plus over Flash?

Choose Plus when answers on complex or long media matter more than speed or cost, such as audits of calls or videos. Flash shares the same inputs and voices, so it is the better default for quick, high-volume tasks.

What inputs does it accept?

Text, images, audio, and video, in any combination within one request. Output can be text or text with speech, and the voice is selectable from 55 built-in options or a custom voice.

How long can a recording be?

Roughly 3 hours of audio or 1 hour of video per request, per Alibaba's documentation for the Plus tier. Split longer material into parts and combine the answers afterwards.

Is there a live-conversation version?

Yes, Qwen3.5-Omni-Plus-Realtime, which runs in a streaming session for live voice. Use Qwen3.5-Omni-Plus for finished recordings and the Realtime model for live conversation with a person.

How many languages does it handle?

Alibaba lists 113 languages for audio input and 74 languages with 39 dialects for audio output. Text understanding covers more languages than spoken output does, so ask in any language.

How much does Qwen3.5-Omni-Plus cost?

On TokenLab, Qwen3.5-Omni-Plus costs Input $1.40 / Output $8.30 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What are the context window and output limit of Qwen3.5-Omni-Plus?

Qwen3.5-Omni-Plus accepts up to 196,608 tokens of context and returns up to 65,536 tokens in one response.

Which endpoint should Qwen3.5-Omni-Plus use?

Use https://api.tokenlab.sh/v1/messages for Qwen3.5-Omni-Plus. The request example below shows the matching code shape.

Which operations does Qwen3.5-Omni-Plus support?

Qwen3.5-Omni-Plus supports Text to text. Select an operation above to see its endpoint and request example.