{"slug": "anthropic-claude-fable-5-on-aws-mythos-class-capabilities-with-built-in-now", "title": "Anthropic Claude Fable 5 on AWS: Mythos-class capabilities with built-in safeguards now available", "summary": "Anthropic has released Claude Fable 5 on Amazon Bedrock and the Claude Platform on AWS, providing customers with Mythos-class AI capabilities that include advanced vision, long-running asynchronous execution, and proactive self-verification. The model incorporates built-in safeguards that restrict its performance in high-risk areas such as cybersecurity and biology, with harmful prompts redirected to the less capable Opus 4.8 model. The full capabilities without these limits are reserved for a small group of vetted customers through the separate Claude Mythos 5 release.", "body_md": "[AWS News Blog](https://aws.amazon.com/blogs/aws/)\n\n# Anthropic Claude Fable 5 on AWS: Mythos-class capabilities with built-in safeguards now available\n\n|\n|\n\nToday, we’re announcing the availability of [Claude Fable 5](https://www.anthropic.com/news/claude-fable-5-mythos-5) on [Amazon Bedrock](https://aws.amazon.com/bedrock/?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el) and [Claude Platform on AWS](https://aws.amazon.com/claude-platform/?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el). Claude Fable 5 makes Mythos-level capabilities available to customers, with strong safeguards designed to make it safe for broader use. Fable 5 is state-of-the-art on nearly all tested benchmarks and delivers exceptional performance in software engineering, knowledge work tasks, and vision – built for ambitious, long running work.\n\nWith Claude Fable 5 on Bedrock, you can build within your existing AWS environment and scale inference workloads. You can also use Claude Fable 5 through the Claude Platform on AWS, giving you Anthropic’s native platform experience.\n\nAccording to Anthropic, Claude Fable 5 represents a step-change in what you can accomplish with AI models. Here is what makes this model different:\n\n**Long-running, asynchronous execution**— Claude Fable 5 handles complex tasks that previous models could not sustain, executing coding and knowledge work tasks for extended periods without intervention.**Advanced vision capabilities**— Claude Fable 5 understands diagrams, charts, and tables nested in files and PDFs. This opens up research and document-heavy work in finance, legal, analytics, architecture, and gaming. In coding, the model implements designs with high fidelity and uses vision to critique its output against goals.**Proactive self-verification**— The model updates its own skills based on learnings and develops its own harnesses and evaluations.\n\nClaude Fable 5 includes safeguards that limit its performance in specific areas where misuse risk is elevated. Harmful prompts related to cybersecurity, biology, chemistry, and health fall back to receive a response from Opus 4.8 instead. Anthropic is able to expand access to nearly all of Claude Fable 5’s state-of-the-art capabilities by developing more powerful safeguards. The same model without these limits is [Claude Mythos 5](https://www.anthropic.com/news/claude-fable-5-mythos-5) and it will only be available to a small group of vetted customers.\n\n__Claude Fable 5 model in action__\n\nYou can use Claude Fable 5 in both Amazon Bedrock and Claude Platform on AWS. This post covers guidance on how to access and use on Amazon Bedrock. For guidance on the Claude Platform on AWS, visit the [documentation](https://docs.aws.amazon.com/claude-platform/latest/userguide/welcome.html?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el) to learn more.\n\nTo get started with Amazon Bedrock, you can access the model programmatically now using the [Anthropic Messages API](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el) to call the `bedrock-runtime`\n\nor `bedrock-mantle`\n\nendpoints through Anthropic SDK. You can also keep using the [Invoke](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-api.html) and [Converse API](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el) on `bedrock-runtime`\n\nthrough the [AWS Command Line Interface (AWS CLI)](https://aws.amazon.com/cli/?trk=769a1a2b-8c19-4976-9c45-b6b1226c7d20&sc_channel=el) and [AWS SDK](https://aws.amazon.com/developer/tools/?trk=769a1a2b-8c19-4976-9c45-b6b1226c7d20&sc_channel=el).\n\n**Configure data retention setting\n**In order to access Claude Fable 5 model, you must opt into data sharing by using the\n\n[Data Retention API](https://docs.aws.amazon.com/bedrock/latest/userguide/data-retention.html?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el)and setting\n\n`provider_data_share`\n\nbefore you can invoke the models. There is no console user interface for this setting at launch.This mode allows Amazon Bedrock to retain and share your inference data with model providers per their requirements. Anthropic requires 30-day inputs and outputs retention, as well as human review. To learn more, visit the [Amazon Bedrock abuse detection](https://docs.aws.amazon.com/bedrock/latest/userguide/abuse-detection.html?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el).\n\nHere is a sample script to set data retention for the `bedrock-mantle`\n\nengine.\n\n```\ncurl -X PUT https://bedrock-mantle.us-east-1.api.aws/v1/data_retention \\\n  -H \"x-api-key: <your-bedrock-api-key>\" \\ \n  -H \"Content-Type: application/json\" \\\n  -d '{ \"mode\": \"provider_data_share\" }'\n```\n\nIf you want to use the `bedrock-runtime`\n\nengine, run this sample script.\n\n```\ncurl -X PUT https://bedrock.us-east-1.amazonaws.com/data-retention \\\n  -H \"Authorization: Bearer <your_bearer_token>\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{ \"mode\": \"provider_data_share\" }'\n```\n\n**Updated on Jun 10, 2026** — You can also use AWS SigV4 (Signature Version 4) to call the data retention API. Configure your AWS CLI or AWS SDK using environment variables.\n\n```\nexport AWS_ACCESS_KEY_ID=your_access_key_id\nexport AWS_SECRET_ACCESS_KEY=your_secret_access_key\nexport AWS_SESSION_TOKEN=your_session_token\n```\n\nFirst, retrieve your current Bedrock data retention settings.\n\n```\ncurl -s https://bedrock.us-east-1.amazonaws.com/data-retention \\\n  --aws-sigv4 \"aws:amz:us-east-1:bedrock\" \\\n  --user \"$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY\" \\\n  -H \"x-amz-security-token: $AWS_SESSION_TOKEN\"\n```\n\nThis should return something like this: `{\"mode\":\"inherit\",\"updatedAt\":null}`\n\nand update the data retention settings.\n\n```\ncurl -s -X PUT https://bedrock.us-east-1.amazonaws.com/data-retention \\\n  --aws-sigv4 \"aws:amz:us-east-1:bedrock\" \\\n  --user \"$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY\" \\\n  -H \"x-amz-security-token: $AWS_SESSION_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"mode\":\"provider_data_share\"}'\n```\n\nIf everything worked as expected, you should receive a response like: `{\"mode\":\"provider_data_share\",\"updatedAt\":\"2026-06-10T16:51:39.331Z\"}`\n\n.\n\nThe latest AWS CLI supports configuring the data retention setting. Set your bearer API key as an environment variable after you generate a API key in the [Bedrock console](https://console.aws.amazon.com/bedrock/home?region=us-east-1#/api-keys).\n\n```\nexport AWS_BEARER_TOKEN_BEDROCK=bedrock-api-key-XXXXXXXXXX\n```\n\nRun the following CLI command to use the Claude Fable 5 model.\n\n```\naws bedrock put-account-data-retention \\ \n  --mode provider_data_share\n```\n\nTo learn more, visit the [Data Retention API](https://docs.aws.amazon.com/bedrock/latest/userguide/data-retention.html?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el) on the Amazon Bedrock User Guide.\n\n**How to use the Claude Fable 5 model\n**Let’s start with Anthropic SDK for Python using the Messages API on\n\n`bedrock-mantle`\n\nendpoint. Install Anthropic SDK.\n\n```\npip install anthropic\n```\n\nHere is a sample Python code to call Claude Fable 5 model:\n\n``` python\nimport anthropic\n\nclient = anthropic.Anthropic(\n    base_url=\"https://bedrock-mantle.us-east-1.api.aws/anthropic\",\n    api_key= <your-bedrock-api-key>\n)\n\nmessage = client.messages.create( \n     model=\"anthropic.claude-fable-5\", \n\t max_tokens=4096, \n\t messages=[ \n\t     { \"role\": \"user\", \n\t\t   \"content\": \"Design a distributed architecture on AWS in Python that should support 100k requests per second across multiple geographic regions\", \n\t\t }, \n\t ], \n)\n\nprint(message.content[0].text)\n```\n\nTo learn more, check out [Anthropic Messages API code examples](https://docs.aws.amazon.com/bedrock/latest/userguide/api-inference-examples-claude-messages-code-examples.html?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el) and [notebook examples](https://github.com/aws-samples/anthropic-on-aws/tree/main/notebooks) for multiple use cases and a variety of programming languages.\n\nYou can use Claude Fable 5 in the [Bedrock console](https://console.aws.amazon.com/bedrock/home?#/playground?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el). Choose **Claude Fable 5** in the **Playground** and test it.\n\nYou can also use Claude Fable 5 with the Invoke API and Converse API on `bedrock-runtime`\n\nendpoint. Here’s an example to call Converse API for a unified multi-model experience using the AWS SDK for Python (Boto3):\n\n``` python\nimport boto3 \nbedrock_runtime = boto3.client(\"bedrock-runtime\", region_name=\"us-east-1\") \nresponse = bedrock_runtime.converse( \n    modelId=\"global.anthropic.claude-fable-5\", \n    messages=[ \n        { \n            \"role\": \"user\", \n            \"content\": [ \n                { \n                    \"text\": \"Design a distributed architecture on AWS in Python that should support 100k requests per second across multiple geographic regions.\" \n                } \n            ] \n        } \n    ], \n    inferenceConfig={ \n        \"maxTokens\": 4096 \n    } \n) \nprint(response[\"output\"][\"message\"][\"content\"][0][\"text\"])\n```\n\nTo learn more, visit [code examples](https://docs.aws.amazon.com/bedrock/latest/userguide/service_code_examples_bedrock-runtime_anthropic_claude.html) that show how to use Amazon Bedrock Runtime with AWS SDKs.\n\n**Things to know**\n\nLet me share some important technical details that I think you’ll find useful.\n\n**Model access**— Claude Fable 5 access is gradually expanding for all AWS accounts. If your account doesn’t have access yet, it will be enabled soon depending on your Bedrock usage. If you want to get access to this model quickly, contact your usual AWS Support.**Pricing**— When a harmful prompt is routed to Opus 4.8 instead of Fable 5, you pay only Opus prices. If a request is blocked mid-conversation, initial tokens are charged at Fable rates and subsequent tokens at Opus rates. To learn more, visit the[Amazon Bedrock pricing](https://aws.amazon.com/bedrock/pricing/?trk=769a1a2b-8c19-4976-9c45-b6b1226c7d20&sc_channel=el)page.**Data retention**— For Fable 5, Mythos 5, and future models on Bedrock with similar or higher capability levels, Anthropic will require 30-day retention for all traffic on Mythos-class models. Retaining data for a limited period allows Anthropic to detect patterns of misuse that are not visible from a single exchange. Once you opt into data retention, your data will leave AWS’s data and security boundary.**Claude Mythos 5 on Bedrock (Limited Preview)**— You can also use Anthropic’s most capable model for cybersecurity and life sciences, including vulnerability discovery, drug design, and biodefense screening. Access is currently limited due to the dual-use nature of these domains. To learn more, visit the[model card documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-mythos-5.html?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el).\n\n__Now available__\n\nAnthropic’s Claude Fable 5 model is available today on Amazon Bedrock in the US East (N. Virginia) and Europe (Stockholm) Regions; check the [full list of Regions](https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-fable-5.html?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el) for future updates. Claude Fable 5 is also available on the Claude Platform on AWS in North America, South America, Europe, and Asia Pacific.\n\nGive Claude Fable 5 a try with the Amazon Bedrock APIs, in the [Claude Platform on AWS](https://console.aws.amazon.com/claude-platform/?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el), and send feedback to [AWS re:Post for Amazon Bedrock](https://repost.aws/tags/TAQeKlaPaNRQ2tWB6P7KrMag/amazon-bedrock?trk=d8ec3b19-0f37-4f8c-8c12-189f913e205c&sc_channel=el) or through your usual AWS Support contacts.\n\n— [Channy](https://twitter.com/channyun)\n\n**Updated on June 9, 2026** — 1) Updated the console screenshot. You can use the console on `bedrock-runtime`\n\nengine. The console support on `bedrock-mantle`\n\nis coming soon. 2) Fixed the right model id in the sample code, 3) Fixed correct `provider_data_share`\n\nparameter, 4) Add a data retention setting script for `bedrock-runtime`\n\nengine.\n\n**Updated on June 10, 2026** —Added how to configure data retention setting through AWS SigV4 and AWS CLI.", "url": "https://wpnews.pro/news/anthropic-claude-fable-5-on-aws-mythos-class-capabilities-with-built-in-now", "canonical_source": "https://aws.amazon.com/blogs/aws/anthropic-claude-fable-5-on-aws-mythos-class-capabilities-with-built-in-safeguards-now-available/", "published_at": "2026-06-09 17:40:31+00:00", "updated_at": "2026-06-11 19:35:15.381500+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "generative-ai", "ai-safety", "ai-products"], "entities": ["Anthropic", "Claude Fable 5", "Amazon Bedrock", "Claude Platform on AWS", "AWS"], "alternates": {"html": "https://wpnews.pro/news/anthropic-claude-fable-5-on-aws-mythos-class-capabilities-with-built-in-now", "markdown": "https://wpnews.pro/news/anthropic-claude-fable-5-on-aws-mythos-class-capabilities-with-built-in-now.md", "text": "https://wpnews.pro/news/anthropic-claude-fable-5-on-aws-mythos-class-capabilities-with-built-in-now.txt", "jsonld": "https://wpnews.pro/news/anthropic-claude-fable-5-on-aws-mythos-class-capabilities-with-built-in-now.jsonld"}}