Alibaba: Qwen3 VL 235B A22B Instruct

Qwen vision-language instruct model for visual reasoning, documents, and agent tasks

Model lab: Alibaba
Model family: qwen

Model resources

Hugging Face

Modalitiestext, image → text

Context window131,072

Maximum output32,768

InputUSD 0.16 / 1M tokens

OutputUSD 0.704 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to alibaba/qwen3-vl-235b-a22b-instruct.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "alibaba/qwen3-vl-235b-a22b-instruct"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Qwen3 VL 235B A22B Instruct API Pricing

Type	Price information
Input	USD 0.16 / 1M tokens
Output	USD 0.704 / 1M tokens
Cached input	USD 0.088 / 1M tokens

Benchmarks

Intelligence Index · v4.39.9

Coding Index—

Agentic Index—

Performance

Output speed32.6 tokens/s

Time to first token1.22 s

Time to first answer token—

End-to-end response time—

Performance trends

Throughput32.6 tok/sCurrent

Time to first token1.22 sCurrent

End-to-end latency6.9 sCurrent

Throughput

Current32.6 tok/s

Window average32.6 tok/s

Time to first token

Current1.22 s

Window average1.3 s

End-to-end latency

Current6.9 s

Window average7.5 s

Tail latency (P99)

Current13.1 s

Window average16.3 s

Prompt cache hit rate

Current18.0%

Window average24.7%

Error rate

Current0.0%

Window average0.2%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Qwen3 VL 235B A22B Instruct Compare models

Model	Input price	Output price	Context window	Capabilities
Qwen3 VL 235B A22B InstructThis page	USD 0.16 / 1M tokens	USD 0.704 / 1M tokens	131,072	Text output · Tool calling
Qwen3 VL 235B A22B Thinking	USD 0.2296 / 1M tokens	USD 2.2936 / 1M tokens	131,072	Text output · Reasoning · Tool calling
Qwen3-VL Plus	USD 0.1096 / 1M tokens · Base context tier (boundary 32000 tokens)	USD 1.096 / 1M tokens · Base context tier (boundary 32000 tokens)	262,144	Text output · Reasoning · Tool calling
Qwen2.5-VL 72B Instruct	USD 1.8352 / 1M tokens	USD 5.5048 / 1M tokens	131,072	Text output · Tool calling
Qwen-VL Max	USD 0.184 / 1M tokens	USD 0.464 / 1M tokens	131,072	Text output · Tool calling

Model specifications

Input: text, image
Output: text
Context window: 131,072
Maximum output: 32,768
Release date: 2025-09-23
Attachments: Yes
Reasoning: No
Tool calling: Yes
Structured output: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Qwen3 VL 235B A22B Instruct for?

Qwen vision-language instruct model for visual reasoning, documents, and agent tasks

What inputs and outputs does Qwen3 VL 235B A22B Instruct support?

Recorded inputs: text, images; outputs: text.

How is Qwen3 VL 235B A22B Instruct priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.16 / 1M tokens; Output USD 0.704 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Qwen3 VL 235B A22B Instruct?

Current model records list Context window 131,072 tokens; Maximum output 32,768 tokens.

What model parameter does the Quickstart use?

The example uses alibaba/qwen3-vl-235b-a22b-instruct. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.