LLM Reference
AWS Bedrock

Using Claude Mythos 5 on AWS Bedrock

Implementation guide · Claude Mythos · Anthropic

Serverless

AWS Bedrock exposes Claude Mythos 5 through model ID claude-mythos-5. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-26. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at AWS Bedrock and generate an API key.
  2. 2
    Use the AWS Bedrock SDK or REST API to call claude-mythos-5 — see the documentation for request format.

Code Examples

Install
pip install boto3
API key
AWS_ACCESS_KEY_ID
Model ID
claude-mythos-5

Use Amazon Bedrock model IDs, e.g. "anthropic.claude-3-opus-20240229-v1:0" for on-demand, or cross-region inference profile IDs like "us.anthropic.claude-opus-4-7-20251101-v1:0". These differ from the public model slug.

import boto3

# Reads AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGION from env
client = boto3.client("bedrock-runtime", region_name="us-east-1")
response = client.converse(
    modelId="claude-mythos-5",
    messages=[{
        "role": "user",
        "content": [{"text": "Hello"}]
    }]
)
print(response["output"]["message"]["content"][0]["text"])

Pricing on AWS Bedrock

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsCode Execution

About Claude Mythos 5

Anthropic's access-gated frontier model for approved Project Glasswing cybersecurity defenders and biomedical research organizations. Shares the same underlying architecture as Claude Fable 5 but operates with safety classifiers lifted in specific domains: cybersecurity safeguards are removed for all Glasswing participants, while biology safeguards are additionally removed for approved biology-track participants. Succeeds Claude Mythos Preview with significantly reduced pricing ($10/$50 per MTok input/output vs. $25/$125 for Mythos Preview), a 1M-token context window, 128k max output tokens, adaptive thinking always on (raw chain of thought never returned), vision, tool use, structured outputs, and the effort parameter for controlling thinking depth.

Model Specs

Released2026-06-09
Context1m
ArchitectureDecoder Only

Provider

AWS Bedrock
AWS Bedrock

Amazon Web Services

Seattle, Washington, United States