Alibaba: Qwen3 30B A3B

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

Model lab: Alibaba
Model family: qwen

Model resources

Hugging Face

Modalitiestext → text

Context window131,072

Maximum output16,384

InputUSD 0.0864 / 1M tokens

OutputUSD 0.8608 / 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/qwen3-30b-a3b.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "alibaba/qwen3-30b-a3b"

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 30B A3B API Pricing

Type	Price information
Input	USD 0.0864 / 1M tokens
Output	USD 0.8608 / 1M tokens
Cached input	USD 0.01728 / 1M tokens

Benchmarks

Non-reasoning

Intelligence Index · v4.36.6

Coding Index—

Agentic Index—

Performance

Output speed132.92 tokens/s

Time to first token0.56 s

Time to first answer token—

End-to-end response time—

Measurement variant	Output speed	Time to first token	Time to first answer token	End-to-end response time
Non-reasoning	132.92 tokens/s	0.56 s	—	—

Performance trends

Throughput132.92 tok/sCurrent

Time to first token0.56 sCurrent

End-to-end latency7.0 sCurrent

Throughput

Current132.92 tok/s

Window average130.1 tok/s

Time to first token

Current0.56 s

Window average0.6 s

End-to-end latency

Current7.0 s

Window average7.5 s

Tail latency (P99)

Current15.5 s

Window average16.7 s

Prompt cache hit rate

Current31.3%

Window average22.5%

Error rate

Current0.0%

Window average0.1%

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 30B A3B Compare models

Model	Input price	Output price	Context window	Capabilities
Qwen3 30B A3BThis page	USD 0.0864 / 1M tokens	USD 0.8608 / 1M tokens	131,072	Text output · Reasoning · Tool calling
Qwen3.8 2.4T A95B	USD 1.56 / 1M tokens	USD 4.56 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Qwen3.7 Max	USD 0.66 / 1M tokens	USD 1.9804 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
Qwen3.6 Max Preview	USD 1.72 / 1M tokens	USD 10.288 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Qwen3 Coder Next	USD 0.0864 / 1M tokens	USD 0.54 / 1M tokens	262,144	Text output · Tool calling

Model specifications

Input: text
Output: text
Context window: 131,072
Maximum output: 16,384
Release date: 2025-04-28
Attachments: No
Reasoning: Yes
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Qwen3 30B A3B for?

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

What inputs and outputs does Qwen3 30B A3B support?

Recorded inputs: text; outputs: text.

How is Qwen3 30B A3B priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.0864 / 1M tokens; Output USD 0.8608 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Qwen3 30B A3B?

Current model records list Context window 131,072 tokens; Maximum output 16,384 tokens.

What model parameter does the Quickstart use?

The example uses alibaba/qwen3-30b-a3b. 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.