

# Qwen3 235B A22B 2507
<a name="model-card-qwen-qwen3-235b-a22b-2507"></a>

## ![\[alt text not found\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/models/qwen.png) Qwen — Qwen3 235B A22B 2507
<a name="model-card-qwen-qwen3-235b-a22b-2507-header"></a>

## Model Details
<a name="model-card-qwen-qwen3-235b-a22b-2507-details"></a>

Qwen3 235B A22B is Qwen's 235-billion parameter mixture-of-experts model with 22 billion active parameters, supporting text and code generation with a 128K context window. For more information about model development and performance, see the [model/service card](https://qwen.ai/blog?id=qwen3).
+ **Model launch date:** Apr 28, 2025
+ **Model EOL date:** N/A
+ **End User License Agreements and Terms of Use:** [View](https://aws.amazon.com/legal/bedrock/third-party-models/)
+ **Model lifecycle:** Active
+ **Context window:** 128K tokens
+ **Max output tokens:** 8K
+ **Reasoning:** Supported


| **Input Modalities** | **Output Modalities** | **[APIs supported](https://docs.aws.amazon.com/bedrock/latest/userguide/apis.html)** | **[Endpoints supported](https://docs.aws.amazon.com/bedrock/latest/userguide/endpoints.html)** | 
| --- | --- | --- | --- | 
| ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) Audio | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) Embedding | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) Responses | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) bedrock-runtime | 
| ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) Image | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) Image | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) Chat Completions | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) bedrock-mantle | 
| ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) Speech | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) Speech | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) Invoke |  | 
| ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) Text | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) Text | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) Converse |  | 
| ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) Video | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) Video |  |  | 

**Note**  
Whenever possible, we recommend you use the `bedrock-mantle` endpoint.

## Capabilities and Features
<a name="model-card-qwen-qwen3-235b-a22b-2507-capabilities"></a>

***Bedrock Features***

**Features supported using `bedrock-mantle` endpoint**


| **Supported** | **Not Supported** | 
| --- | --- | 
|  [\[See the AWS documentation website for more details\]](http://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html)  |  [\[See the AWS documentation website for more details\]](http://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html)  | 

**Features supported using `bedrock-runtime` endpoint**


| **Supported** | **Not Supported** | 
| --- | --- | 
|  [\[See the AWS documentation website for more details\]](http://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html)  |  [\[See the AWS documentation website for more details\]](http://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html)  | 

## Pricing
<a name="model-card-qwen-qwen3-235b-a22b-2507-pricing"></a>

For pricing, please refer to the [Amazon Bedrock Pricing](https://aws.amazon.com/bedrock/pricing/) page.

## Programmatic Access
<a name="model-card-qwen-qwen3-235b-a22b-2507-programmatic-access"></a>

Use the following model IDs and endpoint URLs to access this model programmatically. For more information about the available APIs and endpoints, see [APIs supported](https://docs.aws.amazon.com/bedrock/latest/userguide/apis.html) and [Endpoints supported](https://docs.aws.amazon.com/bedrock/latest/userguide/endpoints.html).


| **Endpoint** | **Model ID** | **In-Region endpoint URL** | **Geo inference ID** | **Global inference ID** | 
| --- | --- | --- | --- | --- | 
| bedrock-runtime | qwen.qwen3-235b-a22b-2507-v1:0 | https://bedrock-runtime.\$1region\$1.amazonaws.com | Not supported | Not supported | 
| bedrock-mantle | qwen.qwen3-235b-a22b-2507 | https://bedrock-mantle.\$1region\$1.api.aws/v1 | Not supported | Not supported | 

*For example, if region is us-east-1 (N. Virginia), then the bedrock-runtime endpoint URL will be "https://bedrock-runtime.us-east-1.amazonaws.com" and for bedrock-mantle will be "https://bedrock-mantle.us-east-1.api.aws/v1".*

## Service Tiers
<a name="model-card-qwen-qwen3-235b-a22b-2507-tiers"></a>

Amazon Bedrock offers multiple service tiers to match your workload requirements. **Standard** provides pay-per-token access with no commitment. **Priority** offers higher throughput with a time-based commitment. **Flex** provides lower-cost access for flexible, non-time-sensitive workloads. **Reserved** provides dedicated throughput with a term commitment for predictable workloads. For more information, see [service tiers](https://docs.aws.amazon.com/bedrock/latest/userguide/service-tiers-inference.html).


| **Standard** | **Priority** | **Flex** | **Reserved** | 
| --- | --- | --- | --- | 
| ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | 

## Regional Availability
<a name="model-card-qwen-qwen3-235b-a22b-2507-regional-availability"></a>

***Regional availability at a glance***

Bedrock offers three inference options: **In-Region** keeps requests within a single Region for strict compliance, **Geo Cross-Region** routes across Regions within a geography (US, EU, etc.) for higher throughput while respecting data residency, and **Global Cross-Region** routes anywhere worldwide for maximum throughput when there are no residency constraints. Refer to the [Regional availability](models-region-compatibility.md) page for more details.


| **Region** | **In-Region** | **Geo** | **Global** | 
| --- | --- | --- | --- | 
| us-east-2 (Ohio) | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | 
| us-west-2 (Oregon) | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | 
| eu-central-1 (Frankfurt) | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | 
| eu-north-1 (Stockholm) | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | 
| eu-south-1 (Milan) | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | 
| eu-west-2 (London) | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | 
| ap-northeast-1 (Tokyo) | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | 
| ap-south-1 (Mumbai) | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | 
| ap-southeast-2 (Sydney) | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | 
| ap-southeast-3 (Jakarta) | ![\[Yes\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-yes.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | ![\[No\]](http://docs.aws.amazon.com/bedrock/latest/userguide/images/icons/icon-no.png) | 

## Sample Code
<a name="model-card-qwen-qwen3-235b-a22b-2507-sample-code"></a>

**Step 1 - AWS Account:** If you have an AWS account already, skip this step. If you are new to AWS, sign up for an [AWS account](https://portal.aws.amazon.com/billing/signup).

**Step 2 - API key:** Go to the [Amazon Bedrock console](https://console.aws.amazon.com/bedrock/home#/api-keys/long-term/create) and generate a long-term API key.

**Step 3 - Get the SDK:** To use this getting started guide, you must have Python already installed. Then install the relevant software depending on the APIs you are using.

------
#### [ Responses/Chat Completions API ]

```
pip install boto3 openai
```

------
#### [ Invoke/Converse API ]

```
pip install boto3
```

------

**Step 4 - Set environment variables:** Configure your environment to use the API key for authentication.

------
#### [ Responses/Chat Completions API ]

```
OPENAI_API_KEY="<provide your Bedrock API key>"
OPENAI_BASE_URL="https://bedrock-mantle.<your-region>.api.aws/v1"
```

------
#### [ Invoke/Converse API ]

```
AWS_BEARER_TOKEN_BEDROCK="<provide your Bedrock API key>"
```

------

**Step 5 - Run your first inference request:** Save the file as `bedrock-first-request.py`

------
#### [ Responses API ]

```
from openai import OpenAI

client = OpenAI()

response = client.responses.create(
    model="qwen.qwen3-235b-a22b-2507",
    input="Can you explain the features of Amazon Bedrock?"
    )
print(response)
```

------
#### [ Chat Completions API ]

```
from openai import OpenAI

client = OpenAI()

response = client.chat.completions.create(
    model="qwen.qwen3-235b-a22b-2507",
    messages=[{"role": "user", "content": "Can you explain the features of Amazon Bedrock?"}]
    )
print(response)
```

------
#### [ Invoke API ]

```
import json
import boto3

client = boto3.client('bedrock-runtime', region_name='us-east-1')
response = client.invoke_model(
    modelId='qwen.qwen3-235b-a22b-2507-v1:0',
    body=json.dumps({
            'messages': [{ 'role': 'user', 'content': 'Can you explain the features of Amazon Bedrock?'}],
            'max_tokens': 1024
    })
 )
 print(json.loads(response['body'].read()))
```

------
#### [ Converse API ]

```
import boto3

client = boto3.client('bedrock-runtime', region_name='us-east-1')
response = client.converse(
    modelId='qwen.qwen3-235b-a22b-2507-v1:0',
    messages=[
        {
            'role': 'user',
            'content': [{'text': 'Can you explain the features of Amazon Bedrock?'}]
        }
    ]
)
print(response)
```

------