# Claude Opus 4.8
##  Anthropic — Claude Opus 4.8
## Model Details
Claude Opus 4.8 is an Anthropic Opus model optimized for coding, agents, and deeper reasoning in enterprise workflows.
+ **Model launch date:** May 28, 2026
+ **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:** 1M tokens
+ **Max output tokens:** 128K
+ **Reasoning:** Supported
+ **Knowledge cutoff:** January 2026
+ **Marketplace product ID:** `prod-bk5rjg4eo2pke`
| **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)** |
| --- | --- | --- | --- |
|  Audio |  Embedding |  Responses |  bedrock-runtime |
|  Image |  Image |  Chat Completions |  bedrock-mantle |
|  Speech |  Speech |  Invoke | |
|  Text |  Text |  Converse | |
|  Video |  Video |  Messages | |
## Capabilities and Features
***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-anthropic-claude-opus-4-8.html) | [See the AWS documentation website for more details](http://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-8.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-anthropic-claude-opus-4-8.html) | [See the AWS documentation website for more details](http://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-8.html) |
**Prompt caching**
For more information, see [Prompt caching for faster model inference](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html).
| **Prompt caching supported** | **Min tokens per cache checkpoint** | **Max cache checkpoints per request** | **Supported TTL** | **Fields that accept prompt cache checkpoints** |
| --- | --- | --- | --- | --- |
| Yes | 4,096 | 4 | 5 minutes, 1 hour | system, messages, and tools |
**Computer use using `bedrock-runtime` and `bedrock-mantle` endpoints**
For more information, see [Computer use](https://docs.aws.amazon.com/bedrock/latest/userguide/computer-use.html).
| **Tool type** | **Beta header** |
| --- | --- |
| computer\_20251124 | computer-use-2025-11-24 |
## Pricing
For pricing, please refer to the [Amazon Bedrock Pricing](https://aws.amazon.com/bedrock/pricing/) page.
## Programmatic Access
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 | anthropic.claude-opus-4-8 | N/A | `us.anthropic.claude-opus-4-8`
`eu.anthropic.claude-opus-4-8`
`jp.anthropic.claude-opus-4-8`
`au.anthropic.claude-opus-4-8` | global.anthropic.claude-opus-4-8 |
| bedrock-mantle | anthropic.claude-opus-4-8 | https://bedrock-mantle.{region}.api.aws/anthropic/v1/messages | N/A | N/A |
*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/anthropic/v1/messages".*
## Service Tiers
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** |
| --- | --- | --- | --- |
|  |  |  |  |
## Regional Availability
***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.
+ **Global Cross-Region** routes anywhere worldwide for maximum throughput when there are no residency constraints.
For more details, see the [Regional availability by models](models-region-compatibility.md) page.
| **Region** | **In-Region** | **Geo** | **Global** |
| --- | --- | --- | --- |
| us-east-1 (N. Virginia) |  |  |  |
| us-east-2 (Ohio) |  |  |  |
| us-west-1 (N. California) |  |  |  |
| us-west-2 (Oregon) |  |  |  |
| ca-central-1 (Canada) |  |  |  |
| ca-west-1 (Calgary) |  |  |  |
| eu-central-1 (Frankfurt) |  |  |  |
| eu-central-2 (Zurich) |  |  |  |
| eu-north-1 (Stockholm) |  |  |  |
| eu-south-1 (Milan) |  |  |  |
| eu-south-2 (Spain) |  |  |  |
| eu-west-1 (Ireland) |  |  |  |
| eu-west-2 (London) |  |  |  |
| eu-west-3 (Paris) |  |  |  |
| ap-east-2 (Taipei) |  |  |  |
| ap-northeast-1 (Tokyo) |  |  |  |
| ap-northeast-2 (Seoul) |  |  |  |
| ap-northeast-3 (Osaka) |  |  |  |
| ap-south-1 (Mumbai) |  |  |  |
| ap-south-2 (Hyderabad) |  |  |  |
| ap-southeast-1 (Singapore) |  |  |  |
| ap-southeast-2 (Sydney) |  |  |  |
| ap-southeast-3 (Jakarta) |  |  |  |
| ap-southeast-4 (Melbourne) |  |  |  |
| ap-southeast-5 (Malaysia) |  |  |  |
| ap-southeast-6 (New Zealand) |  |  |  |
| ap-southeast-7 (Thailand) |  |  |  |
| il-central-1 (Tel Aviv) |  |  |  |
| me-central-1 (UAE) |  |  |  |
| me-south-1 (Bahrain) |  |  |  |
| af-south-1 (Cape Town) |  |  |  |
| sa-east-1 (São Paulo) |  |  |  |
| mx-central-1 (Mexico) |  |  |  |
***Geo inference details***
**Geo: US**
Geo Inference ID: `us.anthropic.claude-opus-4-8`
| **Source Region** | **Destination Regions** |
| --- | --- |
| us-east-1 (N. Virginia) | us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-2 (Oregon) |
| us-east-2 (Ohio) | us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-2 (Oregon) |
| us-west-1 (N. California) | us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-1 (N. California), us-west-2 (Oregon) |
| us-west-2 (Oregon) | us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-2 (Oregon) |
| ca-central-1 (Canada) | ca-central-1 (Canada), us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-2 (Oregon) |
| ca-west-1 (Calgary) | ca-west-1 (Calgary), us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-2 (Oregon) |
**Geo: EU**
Geo Inference ID: `eu.anthropic.claude-opus-4-8`
| **Source Region** | **Destination Regions** |
| --- | --- |
| eu-central-1 (Frankfurt) | eu-central-1 (Frankfurt), eu-north-1 (Stockholm), eu-south-1 (Milan), eu-south-2 (Spain), eu-west-1 (Ireland), eu-west-3 (Paris) |
| eu-central-2 (Zurich) | eu-central-1 (Frankfurt), eu-central-2 (Zurich), eu-north-1 (Stockholm), eu-south-1 (Milan), eu-south-2 (Spain), eu-west-1 (Ireland), eu-west-3 (Paris) |
| eu-north-1 (Stockholm) | eu-central-1 (Frankfurt), eu-north-1 (Stockholm), eu-south-1 (Milan), eu-south-2 (Spain), eu-west-1 (Ireland), eu-west-3 (Paris) |
| eu-south-1 (Milan) | eu-central-1 (Frankfurt), eu-north-1 (Stockholm), eu-south-1 (Milan), eu-south-2 (Spain), eu-west-1 (Ireland), eu-west-3 (Paris) |
| eu-south-2 (Spain) | eu-central-1 (Frankfurt), eu-north-1 (Stockholm), eu-south-1 (Milan), eu-south-2 (Spain), eu-west-1 (Ireland), eu-west-3 (Paris) |
| eu-west-1 (Ireland) | eu-central-1 (Frankfurt), eu-north-1 (Stockholm), eu-south-1 (Milan), eu-south-2 (Spain), eu-west-1 (Ireland), eu-west-3 (Paris) |
| eu-west-2 (London) | eu-central-1 (Frankfurt), eu-north-1 (Stockholm), eu-south-1 (Milan), eu-south-2 (Spain), eu-west-1 (Ireland), eu-west-2 (London), eu-west-3 (Paris) |
| eu-west-3 (Paris) | eu-central-1 (Frankfurt), eu-north-1 (Stockholm), eu-south-1 (Milan), eu-south-2 (Spain), eu-west-1 (Ireland), eu-west-3 (Paris) |
**Geo: JP**
Geo Inference ID: `jp.anthropic.claude-opus-4-8`
| **Source Region** | **Destination Regions** |
| --- | --- |
| ap-northeast-1 (Tokyo) | ap-northeast-1 (Tokyo), ap-northeast-3 (Osaka) |
| ap-northeast-3 (Osaka) | ap-northeast-1 (Tokyo), ap-northeast-3 (Osaka) |
**Geo: AU**
Geo Inference ID: `au.anthropic.claude-opus-4-8`
| **Source Region** | **Destination Regions** |
| --- | --- |
| ap-southeast-2 (Sydney) | ap-southeast-2 (Sydney), ap-southeast-4 (Melbourne) |
| ap-southeast-4 (Melbourne) | ap-southeast-2 (Sydney), ap-southeast-4 (Melbourne) |
***Global inference details***
| **Global Inference ID** | **Americas** | **EMEA** | **Asia Pacific** |
| --- | --- | --- | --- |
| global.anthropic.claude-opus-4-8 | [See the AWS documentation website for more details](http://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-8.html) | [See the AWS documentation website for more details](http://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-8.html) | [See the AWS documentation website for more details](http://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-8.html) |
## Quotas and Limits
Your AWS account has default quotas for Amazon Bedrock. These quotas might change depending on regional factors, payment history, or approval of a quota [increase request](https://docs.aws.amazon.com/bedrock/latest/userguide/quotas-increase.html). For more details, see [Quotas for Amazon Bedrock](quotas.md) and the [limits](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#limits_bedrock) for the model.
Default quotas for Claude Opus 4.8 are 20M input TPM and 4M output TPM on `bedrock-mantle` and 30M TPM on `bedrock-runtime` for each supported region. Claude Opus 4.8 does not have a requests-per-minute (RPM) quota; throttling is governed solely by the token-per-minute (TPM) quotas above.
## Sample Code
**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.
------
#### [ Messages API ]
```
pip install -U "anthropic[bedrock]"
```
------
#### [ Invoke/Converse API ]
```
pip install boto3
```
------
**Step 4 - Set environment variables:** Configure your environment to use the API key for authentication.
------
#### [ Messages API ]
```
AWS_BEARER_TOKEN_BEDROCK=""
```
------
#### [ Invoke/Converse API ]
```
AWS_BEARER_TOKEN_BEDROCK=""
```
------
**Step 5 - Run your first inference request:** Save the file as `bedrock-first-request.py`
------
#### [ Messages API ]
```
from anthropic import AnthropicBedrockMantle
client = AnthropicBedrockMantle(aws_region="us-east-1")
message = client.messages.create(
model="anthropic.claude-opus-4-8",
max_tokens=1024,
messages=[{"role": "user", "content": "Can you explain the features of Amazon Bedrock?"}],
)
print(message.content[0].text)
```
------
#### [ Invoke API ]
```
import json
import boto3
client = boto3.client('bedrock-runtime', region_name='us-east-1')
response = client.invoke_model(
modelId='anthropic.claude-opus-4-8',
body=json.dumps({
'anthropic_version': 'bedrock-2023-05-31',
'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='anthropic.claude-opus-4-8',
messages=[
{
'role': 'user',
'content': [{'text': 'Can you explain the features of Amazon Bedrock?'}]
}
]
)
print(response)
```
------