qwen3-5-omni-plus

Models/qwen3.5-omni-plus

Model Code

qwen3.5-omni-plus

Model overview

Qwen3.5Omni-modal

Qwen3.5-Omni-Plus is Qwen's latest omni-modal model. It supports text, image, audio, and audio-video understanding and interaction, more than 10 hours of audio understanding, over 400 seconds of 720P 1 FPS audio-video understanding, 60+ input audio languages, 30+ speech output languages, and structured audio-video understanding.

Company: AlibabaProvider: Alibaba Cloud

Model capabilities

Input modalityT

Output modalityT

Model experience✓

Function calling-

Structured output-

Web search-

Prefix completion-

Context cache✓

Batch inference✓

Fine-tuning-

Model pricing

Audio input$7.91/1M tokens

Text / image / video input$1.04/1M tokens

Text + audio output (text output is not charged)$31.79/1M tokens

Text output$5.97/1M tokens

Tool call pricing

Completions API $0.597/1K calls

Rate limits and context

Maximum input length192K

Context length256K

Maximum output length64K

RPM60

TPM100000

API reference

EndpointPOST /v1/chat/completions

SDKOpenAI-compatible

API code examples

Get API Key

from openai import OpenAI

client = OpenAI(
    api_key="$WLROUTER_API_KEY",
    base_url="https://api.wlrouter.com/v1"
)

response = client.chat.completions.create(
    model="qwen3.5-omni-plus",
    messages=[
        {"role": "user", "content": "Reply with one short sentence."}
    ],
    max_tokens=32
)

print(response.choices[0].message.content)