Speed
Output tokens / second
Qwen3.5 Omni Plus overview
Qwen3.5 Omni Plus by Alibaba Cloud
Qwen3.5 Omni Plus is Alibaba's most advanced omnimodal model: a single system that processes text, images, audio, and video simultaneously, and talks back in natural, streaming speech across 36 languages.
Qwen3.5 Omni Plus specs
- Model ID
alibaba/qwen3.5-omni-plus- Developer
- Alibaba Cloud
- Context window
- 256,000 tokens
- Max output
- 192,000 tokens
- Input
- Text, Image, Audio, Video
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Model Overview
Most AI models you interact with are fundamentally text systems wearing costumes. Voice gets transcribed. Images get captioned. Video gets sampled into frames. Everything quietly converts to text, then converts back. That pipeline works, but it's slow, lossy, and brittle under real-world conditions.
Qwen3.5 Omni Plus is built differently. It's what Alibaba's Qwen team calls a native omnimodal model, one that was trained from the ground up to read, listen, see, and speak as a single unified system. There's no conversion step. There's no stitching. When you send it a video clip with background noise, it doesn't reach for Whisper on one side and a vision encoder on the other. It processes the audio and the visuals together, the way you actually would.
How It Works
Understanding why Qwen3.5 Omni Plus works the way it does means understanding the Thinker–Talker architecture, first introduced in Qwen2.5-Omni and now significantly upgraded in this release.
The Thinker
The Thinker is the reasoning core. It takes in any combination of text, image, audio, or video input, processes it through a Hybrid-Attention Mixture-of-Experts (MoE) design, and produces the underlying understanding and response. By adopting MoE, the Thinker activates only the parameters needed for a given task, keeping inference efficient even at hundreds-of-billions-of-parameter scale.
The Talker
The Talker converts the Thinker's output into streaming speech. It also uses MoE and introduces a crucial new capability: multi-codebook codec representation for immediate, single-frame synthesis. Instead of generating speech in large batches, the Talker produces audio tokens one frame at a time, cutting latency noticeably compared to earlier approaches.
Aligning Text and Speech on the Fly
Speech synthesis has always struggled with one specific problem: text tokenizers and audio tokenizers don't process information at the same rate, which creates instability and unnatural-sounding output. ARIA, the model's new alignment technique, dynamically synchronizes text and speech units during streaming decoding. The practical result is more natural prosody and significantly more stable multilingual output, without meaningful latency overhead.
TMRoPE and Long-Context Audio-Visual Reasoning
Earlier Qwen models used TMRoPE (Temporal Multimodal Rotary Position Embedding) to give the model awareness of time within a sequence. Qwen3.5 Omni Plus refines this approach to avoid the sparse temporal position IDs that caused degraded performance on very long inputs. The result is genuinely useful long-context reasoning, not just theoretically supported, but performing reliably on inputs spanning hours of audio or video.
Use cases
It is documented as suited to text creation, voice assistants, and multimedia analysis. It is also described for audio-video analysis, shot breakdown, and content moderation.
For speech-oriented use, it supports offline speech output and voice cloning. It is additionally presented as useful for real-time interaction, including voice dialogue and audiovisual tool use.
Capabilities
- Function calling
- Streaming
- Structured outputs
- Reasoning
Qwen3.5 Omni Plus benchmarks by 
Artificial Analysis
See how Qwen3.5 Omni Plus compares in generation speed and latency. Data retrieved Nov 3, 2026.
Benchmark results
Compare 15 models available on AI/ML API across 5 independent benchmarks.
Humanity's Last Exam
Expert-written questions across academic subjects.
GPQA Diamond
Graduate-level science questions written to resist web search.
AA-LCR
Reasoning across long documents of about 100k tokens.
IFBench
Following precise instructions about the shape of the answer.
τ²-Bench Telecom
Customer support agent tasks with tool calls.
Qwen3.5 Omni Plus API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $1.4 | 1M tokens |
| Output | $8.3 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Qwen3.5 Omni Plus vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Qwen3.5 Omni Plus | $1.4 | $8.3 |
| Qwen3.8 Omni Flash | $0.15 | $0.47 |
| Qwen3.8-Flash | $0.16 | $0.47 |
| Qwen 3.8 27B | $0.4761 | $3.39 |
| Qwen3.8 Max Prime | $4.23 | $12.7 |
How to use the Qwen3.5 Omni Plus API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "alibaba/qwen3.5-omni-plus",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "alibaba/qwen3.5-omni-plus",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "alibaba/qwen3.5-omni-plus",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to Qwen3.5 Omni Plus
Related articles
Qwen3.5 Omni Plus FAQ
What is the context window of Qwen3.5 Omni Plus?
Qwen3.5 Omni Plus has a 256,000 tokens context window and can return up to 192,000 tokens.
What inputs and outputs does Qwen3.5 Omni Plus support?
Qwen3.5 Omni Plus takes audio, image, text, video as input and returns audio, text.
What is the model ID for Qwen3.5 Omni Plus?
Use alibaba/qwen3.5-omni-plus as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
When was Qwen3.5 Omni Plus released?
Qwen3.5 Omni Plus became available on April 24, 2026.
How much does Qwen3.5 Omni Plus cost?
Qwen3.5 Omni Plus costs $1.4 input and $8.3 output per 1M tokens on AI/ML API, billed as you go with no subscription.
Does Qwen3.5 Omni Plus support streaming?
Yes, Qwen3.5 Omni Plus can stream responses as they are generated.
Can Qwen3.5 Omni Plus read images?
Yes, Qwen3.5 Omni Plus accepts image input alongside text.
Who created Qwen3.5 Omni Plus?
Qwen3.5 Omni Plus was built by Alibaba Cloud.
Is Qwen3.5 Omni Plus capable of reasoning tasks?
Yes, it includes reasoning as one of its core capabilities.
Can Qwen3.5 Omni Plus call functions or use tools?
Yes, it supports function calling, tools, and parallel tool calls.