Alibaba: Qwen3-Next 80B-A3B Instruct

Qwen instruction model for multilingual chat, reasoning, and tool use

Model lab: Alibaba
Model family: qwen

Model resources

Hugging Face

Modalitiestext → text

Context window131,072

Maximum output32,768

Input · Quantization fp8 · Service tier flexUSD 0.0576 / 1M tokens

Output · Quantization fp8 · Service tier flexUSD 0.704 / 1M tokens

Try now View docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/alibaba-cloud/qwen3-next-80b-a3b-instruct.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/alibaba-cloud/qwen3-next-80b-a3b-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-Next 80B-A3B Instruct API Pricing

Type	Price information
Input · Quantization fp8 · Service tier flex	USD 0.0576 / 1M tokens
Output · Quantization fp8 · Service tier flex	USD 0.704 / 1M tokens

Benchmarks

Intelligence Index · v4.39.6

Coding Index—

Agentic Index—

Performance

Output speed105.54 tokens/s

Time to first token0.89 s

Time to first answer token—

End-to-end response time—

Performance trends

Throughput105.54 tok/sCurrent

Time to first token0.89 sCurrent

End-to-end latency7.3 sCurrent

Throughput

Current105.54 tok/s

Window average108.3 tok/s

Time to first token

Current0.89 s

Window average0.9 s

End-to-end latency

Current7.3 s

Window average7.5 s

Tail latency (P99)

Current14.1 s

Window average16.5 s

Prompt cache hit rate

Current31.1%

Window average23.1%

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-Next 80B-A3B Instruct Compare models

Model	Input price	Output price	Context window	Capabilities
Qwen3-Next 80B-A3B InstructThis page	USD 0.0576 / 1M tokens · Quantization fp8 · Service tier flex	USD 0.704 / 1M tokens · Quantization fp8 · Service tier flex	131,072	Text output · 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: 32,768
Release date: 2025-09
Attachments: No
Reasoning: No
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Qwen3-Next 80B-A3B Instruct for?

Qwen instruction model for multilingual chat, reasoning, and tool use

What inputs and outputs does Qwen3-Next 80B-A3B Instruct support?

Recorded inputs: text; outputs: text.

How is Qwen3-Next 80B-A3B Instruct priced?

The pricing table shows the current recorded Moduck price. For example: Input · Quantization fp8 · Service tier flex USD 0.0576 / 1M tokens; Output · Quantization fp8 · Service tier flex USD 0.704 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Qwen3-Next 80B-A3B 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 moduck/alibaba-cloud/qwen3-next-80b-a3b-instruct. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

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.