Qwen3-Next-80B-A3B Instruct API

Alibaba's Qwen 3 Next 80B A3B Instruct is a multilingual model with enhanced instruction-following capabilities.

Modalities: TextText
In / Out price: $0.1587/$1.27per 1M
Context window: 126K tokens
Released: Sep 30, 2025

Qwen3-Next-80B-A3B Instruct overview

Qwen3-Next-80B-A3B Instruct by Alibaba Cloud

Qwen3-Next 80B A3B Instruct supports long contexts and efficient reasoning for demanding production AI and coding workflows.

Qwen3-Next-80B-A3B Instruct specs

Model ID: alibaba/qwen3-next-80b-a3b-instruct
Developer: Alibaba Cloud
Context window: 129,024 tokens
Max output: 16,384 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Qwen3-Next-80B-A3B Instruct is a highly efficient instruction-tuned large language model designed for fast, stable responses with ultra-long context handling and high throughput. It activates only a small portion of its 80 billion parameters to achieve significant improvements in speed and cost-efficiency without sacrificing performance in reasoning, code generation, and other complex tasks.

Technical Specifications

Qwen3-Next-80B-A3B Instruct activates only about 3 billion parameters out of 80 billion during inference, making it much faster and cheaper to run, about 10 times faster and more cost-efficient compared to the earlier Qwen3-32B model. It delivers over 10 times higher throughput on long contexts of 32K tokens or more. The model supports flexible deployment options including serverless, on-demand dedicated, and monthly reserved hosting. It is compatible with SGLang and vLLM for deployment with advanced mult-token prediction capabilities, ensuring efficient and scalable usage.

Performance Benchmarks

Performance matches or closely approaches Qwen3-235B flagship in many reasoning, code completion, and instruction-following tasks
Excels in long-context tasks with stable, deterministic answers
Outperforms earlier mid-sized instruction-tuned models, demonstrating efficiency with reduced computational resources
Suitable for tools integration, retrieval-augmented generation (RAG), and agentic workflows requiring consistent chain-of-thought outputs

Key Capabilities

Highly efficient instruction-following with sparse Mixture-of-Experts (MoE) architecture activating only 3B parameters out of 80B, offering faster and cheaper inference.
Exceptional performance on complex tasks including reasoning, code generation, knowledge question answering, and multilingual usage.
Stable and fast responses optimized for instruction mode without intermediate “thinking” steps.
Supports ultra-long context handling with native 262K token length, extendable to 1 million tokens with scaling technology.
High throughput for processing long contexts (10x improvement over previous models).
Excellent for multi-turn dialogues and tasks requiring deterministic, consistent final answers.
Strong capabilities for tool calling, multi-step task execution, and agentic workflows with integrated tools.

Use Cases

Code generation and software development assistance
Content creation and editing based on detailed instructions
Data analysis and complex report generation
Customer service automation with precise instruction handling
Technical documentation generation and format-specific outputs
Process automation including multi-step task execution and tool calling
Handling of long conversations and large documents

Comparison with Other Models

vs Qwen3-235B: The 80B A3B model matches or closely approaches the flagship 235B in reasoning and code tasks but is much more efficient, activating fewer parameters for faster, cheaper inference.

vs GPT-4.1: Qwen3-Next offers comparable instruction-following and long-context capabilities, with an edge in throughput and token window size, making it suitable for extensive document comprehension.

vs Claude 4.1 Opus: Qwen3-Next provides superior performance in multi-turn dialogues and agentic workflows, with more deterministic outputs on very long contexts compared to Claude’s conversational strengths.

vs Gemini 2.5 Flash: Qwen3-Next shows better scaling in ultra-long context handling and multi-token prediction efficiency, giving it an advantage in processing complex, multi-step reasoning tasks.

Use cases

Code generation and software development assistance
Content creation and editing based on detailed instructions
Data analysis and complex report generation
Customer service automation with precise instruction handling
Technical documentation generation and format-specific outputs
Process automation including multi-step task execution and tool calling
Handling of long conversations and large documents

Capabilities

Function calling
Streaming
Structured outputs
Web search

Qwen3-Next-80B-A3B Instruct benchmarks by Artificial Analysis

See how Qwen3-Next-80B-A3B Instruct scores on independent evaluations. Data retrieved Nov 3, 2026.

Humanity's Last Exam#182 / 45812.6%Score GPQA Diamond#173 / 43975.9%Score AA-LCR#173 / 39163.7%Score IFBench#100 / 32560.7%Score

Benchmark results

Compare 13 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Qwen3-Next-80B-A3B Instruct API pricing

Qwen3-Next-80B-A3B Instruct pricing in US dollars
Usage	Price	Unit
Input	$0.1587	1M tokens
Output	$1.27	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Qwen3-Next-80B-A3B Instruct vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Qwen3-Next-80B-A3B Instruct	$0.1587	$1.27
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-Next-80B-A3B Instruct API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export 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-next-80b-a3b-instruct",
  "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-next-80b-a3b-instruct",
    "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-next-80b-a3b-instruct",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Qwen3-Next-80B-A3B Instruct FAQ

What is the context window of Qwen3-Next-80B-A3B Instruct?

Qwen3-Next-80B-A3B Instruct has a 129,024 tokens context window and can return up to 16,384 tokens.

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

Qwen3-Next-80B-A3B Instruct takes text as input and returns text.

What is the model ID for Qwen3-Next-80B-A3B Instruct?

Use alibaba/qwen3-next-80b-a3b-instruct as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was Qwen3-Next-80B-A3B Instruct released?

Qwen3-Next-80B-A3B Instruct became available on September 30, 2025.

How much does Qwen3-Next-80B-A3B Instruct cost?

Qwen3-Next-80B-A3B Instruct costs $0.1587 input and $1.27 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Qwen3-Next-80B-A3B Instruct support streaming?

Yes, Qwen3-Next-80B-A3B Instruct can stream responses as they are generated.

Who created Qwen3-Next-80B-A3B Instruct?

Qwen3-Next-80B-A3B Instruct was built by Alibaba Cloud.

What tool-use and output features does Qwen3-Next-80B-A3B Instruct offer?

It supports parallel tool calls, structured output, function calling, and web search.

Start building with Qwen3-Next-80B-A3B Instruct

Get API key

Qwen3-Next-80B-A3B Instruct API

alibaba/qwen3-next-80b-a3b-instruct

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export 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-next-80b-a3b-instruct",
  "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-next-80b-a3b-instruct",
    "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-next-80b-a3b-instruct",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Qwen3-Next-80B-A3B Instruct API

Qwen3-Next-80B-A3B Instruct overview

Qwen3-Next-80B-A3B Instruct by Alibaba Cloud

Qwen3-Next-80B-A3B Instruct specs

Technical Specifications

Performance Benchmarks

Key Capabilities

Use Cases

Comparison with Other Models

Use cases

Capabilities

Qwen3-Next-80B-A3B Instruct benchmarks by Artificial Analysis

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

Qwen3-Next-80B-A3B Instruct API pricing

Qwen3-Next-80B-A3B Instruct vs other models: token prices

How to use the Qwen3-Next-80B-A3B Instruct API

Build with your agent

1Get your API key

2Make your first request

Related articles

Qwen3-Next-80B-A3B Instruct FAQ

Start building with Qwen3-Next-80B-A3B Instruct

Qwen3-Next-80B-A3B Instruct API

Build with your agent

1Get your API key

2Make your first request

Qwen3-Next-80B-A3B Instruct API

Qwen3-Next-80B-A3B Instruct overview

Qwen3-Next-80B-A3B Instruct by Alibaba Cloud

Qwen3-Next-80B-A3B Instruct specs

Technical Specifications

Performance Benchmarks

Key Capabilities

Use Cases

Comparison with Other Models

Use cases

Capabilities

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

Qwen3-Next-80B-A3B Instruct API pricing

Qwen3-Next-80B-A3B Instruct vs other models: token prices

How to use the Qwen3-Next-80B-A3B Instruct API

Build with your agent

1Get your API key

2Make your first request

Models similar to Qwen3-Next-80B-A3B Instruct

Qwen3.8 Max Prime

Qwen3.8 Omni Flash

Qwen3.8-Flash

Mk1.5

Mk1

Gemma 3 (27B)

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Qwen3-Next-80B-A3B Instruct FAQ

Start building with Qwen3-Next-80B-A3B Instruct