Claude Fable 5.2

Anthropic — Claude Fable 5.2

Model Details

Claude Fable 5.2 is Anthropic's frontier model for technical work, setting a new bar in coding, finance, and the sciences. Fable 5.2 takes on ambiguous problems for days, questions and verifies its own work, and orchestrates subagents to optimize results in a loop.

• Model launch date: November 9, 2026

• EOL no sooner than: November 9, 2027

• Legacy period: 6 months

• Model lifecycle policy: Model lifecycle

• Model EOL date: N/A

• End User License Agreements and Terms of Use: View

• Model lifecycle: Active

• Context window: 1M tokens

• Max output tokens: 128K

• Sampling parameters: temperature must be 1.0 or unset; top_p must be 0.99 or unset; temperature and top_p cannot be specified together; top_k is not supported

• Reasoning: Supported (adaptive thinking is always on and cannot be disabled; effort level configurable — low, medium, high, xhigh, max; default: high) See Adaptive thinking.

• Preserved thinking: Thinking blocks are bound to the model and the conversation prefix that produced them. Replay earlier turns unchanged, or a request returns a 400 error. For more information, see Preserved thinking.

• Knowledge cutoff: June 2026

• Marketplace product ID: prod-m733do2vrmi3o

Input Modalities	Output Modalities
Audio	Embedding
Image	Image
Speech	Speech
Text	Text
Video	Video

Endpoints and APIs supported

The following tables show which endpoints and APIs are supported for Claude Fable 5.2. For more information, see APIs supported by Amazon Bedrock and Inference endpoints supported by Amazon Bedrock.

Endpoint support

Endpoint	Supported
bedrock-runtime

APIs supported on bedrock-runtime endpoint

Messages	Responses	Chat Completions	Converse	Invoke

Tip

Whenever possible, we recommend using the bedrock-runtime endpoint for new applications. See Inference endpoints supported by Amazon Bedrock for details.

Capabilities and Features

Bedrock Features

Features supported using bedrock-runtime endpoint

Supported	Not Supported
Response streaming Prompt caching Abuse detection Guardrails Prompt optimization Knowledge base Model evaluation Prompt management Flows Agents Computer use Structured outputs Watermarking	Count tokens Intelligent prompt routing Implicit Prompt Caching

Prompt caching using bedrock-runtime endpoint

For more information, see Prompt caching for faster model inference.

Prompt caching supported	Min tokens per cache checkpoint	Max cache checkpoints per request	Supported TTL	Fields that accept prompt cache checkpoint
Yes	512	4	5 minutes, 1 hour	system, messages, and tools

Computer use using bedrock-runtime endpoint

For more information, see Computer use.

Tool type	Beta header
computer_20251124	computer-use-2025-11-24

Client tools and toolsets using bedrock-runtime endpoint

For more information, see Tool use.

Tool type	Beta header
computer_toolset_20260801	None required
browser_toolset_20260801	None required
bash_20250124	None required
text_editor_20250728	None required
memory_20250818	None required

Compaction using bedrock-runtime endpoint

For more information, see Compaction.

Compaction supported	Beta value
Yes	compact-2026-09-04, compact-2026-01-12

Content Restrictions

Claude Fable 5.2 includes safety classifiers that block high-risk cybersecurity activities and most research biology tasks. When a classifier blocks a request, the API returns a standard HTTP 200 response with stop_reason: "refusal" and a stop_details object containing the restriction category. Organizations working in these areas can apply for less restrictive access through Anthropic's Cyber Verification Program and Life Sciences Verification Program.

Customers should handle stop_reason: "refusal" as a primary response path. Whether a refused request is billed depends on its category and on whether output had started. For details, see Billing notes.

Fallback credit for refused requests (beta)

When Claude Fable 5.2 refuses a request, the response can include a fallback credit token. Redeem the token when you retry the same request on a fallback model, and the retry is billed for the cached conversation prefix at cache-read rates instead of cache-write rates. Not every refusal carries a token. For more information, see Fallback credit for refused requests (beta).

Supported endpoints	Beta value	Valid fallback models
bedrock-runtime	fallback-credit-2026-07-01	Claude Opus 5 (anthropic.claude-opus-5), Claude Opus 4.8 (anthropic.claude-opus-4-8)

Pricing

For pricing information, see the Amazon 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 and Endpoints supported.

Endpoint	Model ID	In-Region endpoint URL	Geo inference ID	Global inference ID
bedrock-runtime	anthropic.claude-fable-5-2	N/A	us.anthropic.claude-fable-5-2	global.anthropic.claude-fable-5-2

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".

Service Tiers

Amazon Bedrock offers multiple service tiers to match your workload requirements. Standard provides pay-per-token access with no commitment (set "service_tier": "default" or omit the field). Priority delivers the fastest response times for a price premium (set "service_tier": "priority"). Flex provides lower-cost access for flexible, non-time-sensitive workloads (set "service_tier": "flex"). Reserved provides dedicated throughput with a term commitment for predictable workloads; it is set at the account level rather than per request (contact your AWS account team to enable). For more information, see service tiers.

Standard	Priority	Flex	Reserved

Regional Availability

Regional availability at a glance

Amazon 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 (such as US, EU, and APAC) while respecting data residency, and Global Cross-Region routes anywhere worldwide when there are no residency constraints. Refer to the Regional availability by models page for more details.

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)
us-gov-east-1 (GovCloud East)
us-gov-west-1 (GovCloud West)

Geo inference details

The destination Regions available to a geographic inference profile depend on the source Region. To retrieve the current routing configuration, call GetInferenceProfile from the source Region.

Geo: US

Geo inference ID: us.anthropic.claude-fable-5-2

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)

Data Retention

To use this model, you must opt in to AWS review by setting your data retention mode to aws_review via the Data Retention API. For more information, see Amazon Bedrock abuse detection.

Quotas and Limits

Your AWS account has default quotas to maintain the performance of the service and to ensure appropriate usage of Amazon Bedrock. The default quotas assigned to an account might be updated depending on regional factors, payment history, fraudulent usage, and/or approval of a quota increase request. For more information, see Quotas for Amazon Bedrock documentation and see the limits for the model.

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.

Step 2 - API key: Go to the Amazon Bedrock console 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 aws-bedrock-token-generator

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="<provide your Bedrock API key>"

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

Messages API

from anthropic import Anthropic
from aws_bedrock_token_generator import provide_token

token = provide_token(region="us-east-1")

client = Anthropic(
    base_url="https://bedrock-runtime.us-east-1.amazonaws.com/anthropic",
    api_key=token,
)

response = client.messages.create(
    model="global.anthropic.claude-fable-5-2",
    max_tokens=16000,
    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='global.anthropic.claude-fable-5-2',
    body=json.dumps({
            'anthropic_version': 'bedrock-2023-05-31',
            'messages': [{ 'role': 'user', 'content': 'Can you explain the features of Amazon Bedrock?'}],
            'max_tokens': 16000
    })
)
print(json.loads(response['body'].read()))

Converse API

import boto3

client = boto3.client('bedrock-runtime', region_name='us-east-1')
response = client.converse(
    modelId='global.anthropic.claude-fable-5-2',
    messages=[
        {
            'role': 'user',
            'content': [{'text': 'Can you explain the features of Amazon Bedrock?'}]
        }
    ]
)
print(response)