Claude 2.0 Pricing & Token Calculator (Anthropic)

Input / Prompt

$8.00/ 1M tokens

$0.0080 per 1K tokens

Output / Completion

$24.00/ 1M tokens

$0.0240 per 1K tokens

Prompt Cache Read

$2.00/ 1M tokens

Save 75% vs prompt

Batch Inference

$4.00/ 1M in

Save 50% via Batch API

Price Ratio

1 : 3.0

Prompt to completion factor

Regional Reach

2AWS Regions

Compare 2 regions ↓

On Google Cloud Vertex AI

Vertex AI isn't shown for Claude 2.0: Anthropic's models are priced there per geography and context band, and this catalog publishes Claude on Amazon Bedrock only.

Alternatives to Claude 2.0

Option	Price vs Claude 2.0	Why look at it
Claude Opus 5 Compare →	input-37%-$3.00/1M output+4%+$1.00/1M Standard tier, per 1M tokens	Next step down in price from Anthropic (flagship tier)
Claude Mythos 5.1 Compare →	input+25%+$2.00/1M output+108%+$26.00/1M Standard tier, per 1M tokens	Next step up in price from Anthropic (flagship tier)
Claude 2.1 Compare →	inputsame price outputsame price Standard tier, per 1M tokens	Same General line, different version
Claude Opus 5.5 Compare →	input-50%-$4.00/1M output-17%-$4.00/1M Standard tier, per 1M tokens	Also from Anthropic (flagship tier)

Claude 2.0 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 (75% discount on cached context)%

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: $8.00/1M · Output: $24.00/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Claude 2.0 on AWS

Prompt CachingSave ~75%

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

Read Rate: $2.00 / 1M tokens
Write Rate (5m TTL): $10.00 / 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: $4.00 / 1M tokens
Batch Output: $12.00 / 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

Rates by region

Live rates across all 2 available AWS cloud regions

Baseline: $8.00/1M 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)	$8.00	$24.00	—	—	Baseline
us-west-2 US West (Oregon)	$8.00	—	—	—	Baseline

Developer Quickstart

Invoke Claude 2.0 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-2-0-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Claude 2.0."}]
        }
    ],
    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")