Foundation Model · Amazon BedrockMythos FamilyFlagship TierText

Claude Mythos Preview

Amazon Bedrock token pricing and cost optimization reference for Claude Mythos Preview.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 2 AWS regions.

ProviderAnthropic

Maker HQSan Francisco, California, USA

Class / TierFlagship

ModalityText

Prompt CachingSave 90%

Batch APISave 50%

AWS Regions2 Global

Bedrock Model IDanthropic.claude-mythos-preview-v1:0

Input / Prompt

$27.50/ 1M tokens

$0.0275 per 1K tokens

Output / Completion

$137.50/ 1M tokens

$0.1375 per 1K tokens

Prompt Cache Read

$2.75/ 1M tokens

Save 90% vs prompt

Batch Inference

$13.75/ 1M in

Save 50% via Batch API

Price Ratio

1 : 5.0

Prompt to completion factor

Regional Reach

2AWS Regions

Compare 2 regions ↓

Alternatives to Claude Mythos Preview

Option	Price vs Claude Mythos Preview	Why look at it
Claude Opus 4.1 Compare →	input-45%-$12.50/1M output-45%-$62.50/1M Standard tier, per 1M tokens	Next step down in price from Anthropic
Claude Mythos 5 Compare →	input-60%-$16.50/1M output-60%-$82.50/1M Standard tier, per 1M tokens	Same Mythos line, different version
Claude Mythos 5.1 Compare →	input-64%-$17.50/1M output-64%-$87.50/1M Standard tier, per 1M tokens	Also from Anthropic
Claude Fable 5.1 Compare →	input-64%-$17.50/1M output-64%-$87.50/1M Standard tier, per 1M tokens	Also from Anthropic (balanced tier)

Claude Mythos Preview Spend Estimator

Model inference spend by prompt volume, cache hit rate, and batch processing.

Prompt Tokens (Millions / month)

M tokens

Completion Tokens (Millions / month)

M tokens

Prompt Cache Hit Rate(90% discount on cached context)

30%

Batch API Mode50% discount on non-realtime async jobs via S3

Estimated Monthly Spend

$0.00

Fresh Prompts:$0.00

Cached Prompts:$0.00

Completions:$0.00

Active: Input: $27.50/1M · Output: $137.50/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Claude Mythos Preview on AWS

Prompt CachingSave ~90%

Caches repetitive system instructions, schemas, and document prefixes in memory with 5-minute and extended 1-hour TTL tiers.

Read Rate: $2.75 / 1M tokens
Write Rate (5m TTL): $34.38 / 1M tokens
Write Rate (1h TTL): $55.00 / 1M tokens
Ideal for: Multi-turn conversations, RAG document queries, structured schemas

Batch InferenceSave 50%

Asynchronous bulk processing submitted via Amazon S3 with a standard 24-hour turnaround SLA.

Batch Input: $13.75 / 1M tokens
Batch Output: $68.75 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers2 Regions

AWS Bedrock supports standard on-demand inference, priority reserved throughput, and cross-region routing.

Standard: Lowest latency, pay-per-token with zero commitments
Cross-Region Routing: Automatically burst traffic to available regional capacity
GovCloud: Dedicated isolated compliance partitions with +20% uplift

Regional Pricing Matrix

Live rates across all 2 available AWS cloud regions

Baseline: $27.50/1M in2 Global Regions

AWS Region	Prompt Input $/1M	Completion Output $/1M	Cache Read $/1M	Batch Input $/1M	Pricing Tier
us-east-1 US East (N. Virginia)	$27.50	$137.50	$2.75	—	Baseline
ap-southeast-4 Asia Pacific (Melbourne)	$27.50	$137.50	$2.75	—	Baseline

Developer Quickstart

Invoke Claude Mythos Preview via Amazon Bedrock Converse API

Python (boto3) · Amazon Bedrock Runtime

import boto3

# Amazon Bedrock Converse API invocation
client = boto3.client("bedrock-runtime", region_name="us-east-1")

response = client.converse(
    modelId="anthropic.claude-mythos-preview-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Claude Mythos Preview."}]
        }
    ],
    inferenceConfig={
        "maxTokens": 1024,
        "temperature": 0.7
    }
)

output_text = response["output"]["message"]["content"][0]["text"]
usage = response["usage"]
print(f"Response: {output_text}")
print(f"Usage: {usage['inputTokens']} in, {usage['outputTokens']} out")