Qwen fashions at the moment are accessible in Amazon Bedrock

At the moment we’re including Qwen fashions from Alibaba in Amazon Bedrock. With this launch, Amazon Bedrock continues to develop mannequin alternative by including entry to Qwen3 open weight basis fashions (FMs) in a full managed, serverless method. This launch contains 4 fashions: Qwen3-Coder-480B-A35B-Instruct, Qwen3-Coder-30B-A3B-Instruct, Qwen3-235B-A22B-Instruct-2507, and Qwen3-32B (Dense). Collectively, these fashions function each mixture-of-experts (MoE) and dense architectures, offering versatile choices for various utility necessities.

Amazon Bedrock gives entry to industry-leading FMs by way of a unified API with out requiring infrastructure administration. You possibly can entry fashions from a number of mannequin suppliers, combine fashions into your purposes, and scale utilization based mostly on workload necessities. With Amazon Bedrock, buyer information isn’t used to coach the underlying fashions. With the addition of Qwen3 fashions, Amazon Bedrock affords much more choices to be used circumstances like:

• Code era and repository evaluation with prolonged context understanding
• Constructing agentic workflows that orchestrate a number of instruments and APIs for enterprise automation
• Balancing AI prices and efficiency utilizing hybrid considering modes for adaptive reasoning

Qwen3 fashions in Amazon Bedrock
These 4 Qwen3 fashions at the moment are accessible in Amazon Bedrock, every optimized for various efficiency and price necessities:

• Qwen3-Coder-480B-A35B-Instruct – It is a mixture-of-experts (MoE) mannequin with 480B whole parameters and 35B lively parameters. It’s optimized for coding and agentic duties and achieves sturdy ends in benchmarks corresponding to agentic coding, browser use, and gear use. These capabilities make it appropriate for repository-scale code evaluation and multistep workflow automation.
• Qwen3-Coder-30B-A3B-Instruct – It is a MoE mannequin with 30B whole parameters and 3B lively parameters. Particularly optimized for coding duties and instruction-following situations, this mannequin demonstrates sturdy efficiency in code era, evaluation, and debugging throughout a number of programming languages.
• Qwen3-235B-A22B-Instruct-2507 – That is an instruction-tuned MoE mannequin with 235B whole parameters and 22B lively parameters. It delivers aggressive efficiency throughout coding, math, and common reasoning duties, balancing functionality with effectivity.
• Qwen3-32B (Dense) – It is a dense mannequin with 32B parameters. It’s appropriate for real-time or resource-constrained environments corresponding to cell gadgets and edge computing deployments the place constant efficiency is vital.

Architectural and purposeful options in Qwen3
The Qwen3 fashions introduce a number of architectural and purposeful options:

MoE in contrast with dense architectures – MoE fashions corresponding to Qwen3-Coder-480B-A35B, Qwen3-Coder-30B-A3B-Instruct, and Qwen3-235B-A22B-Instruct-2507, activate solely a part of the parameters for every request, offering excessive efficiency with environment friendly inference. The dense Qwen3-32B prompts all parameters, providing extra constant and predictable efficiency.

Agentic capabilities – Qwen3 fashions can deal with multi-step reasoning and structured planning in a single mannequin invocation. They’ll generate outputs that decision exterior instruments or APIs when built-in into an agent framework. The fashions additionally keep prolonged context throughout lengthy classes. As well as, they assist software calling to permit standardized communication with exterior environments.

Hybrid considering modes – Qwen3 introduces a hybrid method to problem-solving, which helps two modes: considering and non-thinking. The considering mode applies step-by-step reasoning earlier than delivering the ultimate reply. That is splendid for advanced issues that require deeper thought. Whereas the non-thinking mode gives quick and near-instant responses for much less advanced duties the place velocity is extra necessary than depth. This helps builders handle efficiency and price trade-offs extra successfully.

Lengthy-context dealing with – The Qwen3-Coder fashions assist prolonged context home windows, with as much as 256K tokens natively and as much as 1 million tokens with extrapolation strategies. This permits the mannequin to course of complete repositories, giant technical paperwork, or lengthy conversational histories inside a single process.

When to make use of every mannequin
The 4 Qwen3 fashions serve distinct use circumstances. Qwen3-Coder-480B-A35B-Instruct is designed for advanced software program engineering situations. It’s suited to superior code era, long-context processing corresponding to repository-level evaluation, and integration with exterior instruments. Qwen3-Coder-30B-A3B-Instruct is especially efficient for duties corresponding to code completion, refactoring, and answering programming-related queries. For those who want versatile efficiency throughout a number of domains, Qwen3-235B-A22B-Instruct-2507 affords a steadiness, delivering sturdy general-purpose reasoning and instruction-following capabilities whereas leveraging the effectivity benefits of its MoE structure. Qwen3-32B (Dense) is acceptable for situations the place constant efficiency, low latency, and price optimization are necessary.

Getting began with Qwen fashions in Amazon Bedrock
To start utilizing Qwen fashions, within the Amazon Bedrock console, I can use the Chat/Textual content Playground part of the navigation pane to shortly take a look at the brand new Qwen fashions with a couple of prompts.

To combine Qwen3 fashions into my purposes, I can use any AWS SDKs. The AWS SDKs embrace entry to the Amazon Bedrock InvokeModel and Converse API. I may use these mannequin with any agentic framework that helps Amazon Bedrock and deploy the brokers utilizing Amazon Bedrock AgentCore. For instance, right here’s the Python code of a easy agent with software entry constructed utilizing Strands Brokers:

from strands import Agent
from strands_tools import calculator

agent = Agent(
    mannequin="qwen.qwen3-coder-480b-a35b-v1:0",
    instruments=[calculator]
)

agent("Inform me the sq. root of 42 ^ 9")

with open("perform.py", 'r') as f:
    my_function_code = f.learn()

agent(f"Assist me optimize this Python perform for higher efficiency:nn{my_function_code}")

Now accessible
Qwen fashions can be found right this moment within the following AWS Areas:

• Qwen3-Coder-480B-A35B-Instruct is out there within the US West (Oregon), Asia Pacific (Mumbai, Tokyo), and Europe (London, Stockholm) Areas.
• Qwen3-Coder-30B-A3B-Instruct, Qwen3-235B-A22B-Instruct-2507, and Qwen3-32B can be found within the US East (N. Virginia), US West (Oregon), Asia Pacific (Mumbai, Tokyo), Europe (Eire, London, Milan, Stockholm), and South America (São Paulo) Areas.

Examine the full Area checklist for future updates. You can begin testing and constructing instantly with out infrastructure setup or capability planning. To be taught extra, go to the Qwen in Amazon Bedrock product web page and the Amazon Bedrock pricing web page.

Attempt Qwen fashions on the Amazon Bedrock console now, and provide suggestions by way of AWS re:Submit for Amazon Bedrock or your typical AWS Assist channels.

— Danilo

Up to date on September 18, 2025 — Eliminated the mannequin entry part. Amazon Bedrock will simplify entry to all serverless basis fashions, and any new fashions, by mechanically enabling them for each AWS account, eliminating the necessity to manually activate entry by way of the Bedrock console. The mannequin entry web page might be retired in October 8, 2025 Account directors retain full management over mannequin entry by way of AWS IAM insurance policies and Service Management Insurance policies (SCPs) to limit mannequin entry as wanted.