Foundation Model ยท Amazon BedrockHaiku FamilyLightweight TierTextMulti-Tier Pricing
Claude Haiku 5.5
Amazon Bedrock token pricing and cost optimization reference for Claude Haiku 5.5.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 35 AWS regions.
ProviderAnthropic
Maker HQSan Francisco, California, USA
Class / TierLightweight
ModalityText
Prompt CachingSave 90%
Batch APISave 50%
AWS Regions35 Global
Bedrock Model ID
anthropic.claude-haiku-5-5-v1:0Input / Prompt
$0.10/ 1M tokens
$0.0001 per 1K tokens
Output / Completion
$0.50/ 1M tokens
$0.0005 per 1K tokens
Prompt Cache Read
$0.01/ 1M tokens
Save 90% vs prompt
Batch Inference
$0.05/ 1M in
Save 50% via Batch API
Price Ratio
1 : 5.0
Prompt to completion factor
Alternatives to Claude Haiku 5.5
| Option | Price vs Claude Haiku 5.5 | Why look at it |
|---|---|---|
| Claude 3 HaikuCompare → | input+150%+$0.15/1M output+150%+$0.75/1M Standard tier, per 1M tokens | Next step up in price from Anthropic |
| Claude 3.5 HaikuCompare → | input+700%+$0.70/1M output+700%+$3.50/1M Standard tier, per 1M tokens | Same Haiku line, different version |
| Claude InstantCompare → | input+700%+$0.70/1M output+380%+$1.90/1M Standard tier, per 1M tokens | Also from Anthropic (general tier) |
| Claude Haiku 4.5Compare → | input+900%+$0.90/1M output+900%+$4.50/1M Standard tier, per 1M tokens | Also from Anthropic |
Claude Haiku 5.5 Spend Estimator
Model inference spend by prompt volume, cache hit rate, and batch processing.
M tokens
M tokens
30%
Estimated Monthly Spend
$0.00
Fresh Prompts:$0.00
Cached Prompts:$0.00
Completions:$0.00
Active: Input: $0.10/1M ยท Output: $0.50/1M
Key Cost Levers & Architecture
Practical mechanisms to reduce inference costs with Claude Haiku 5.5 on AWSPrompt CachingSave ~90%
Caches repetitive system instructions, schemas, and document prefixes in memory with 5-minute and extended 1-hour TTL tiers.
- Read Rate: $0.01 / 1M tokens
- Write Rate (5m TTL): $0.13 / 1M tokens
- Write Rate (1h TTL): $0.20 / 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: $0.05 / 1M tokens
- Batch Output: $0.25 / 1M tokens
- Ideal for: Offline classification, synthetic data generation, benchmark evals
Cross-Region & Tiers35 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 35 available AWS cloud regionsBaseline: $0.10/1M inGovCloud: $0.12/1M in35 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) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| us-west-2 US West (Oregon) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| eu-central-1 Europe (Frankfurt) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| eu-west-1 Europe (Ireland) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-northeast-1 Asia Pacific (Tokyo) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| us-gov-west-1 AWS GovCloud (US-West) | $0.12 | $0.60 | $0.01 | โ | GovCloud (+20%) |
| af-south-1 Africa (Cape Town) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-south-2 Asia Pacific (Hyderabad) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-southeast-3 Asia Pacific (Jakarta) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-southeast-5 Asia Pacific (Malaysia) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-southeast-4 Asia Pacific (Melbourne) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-south-1 Asia Pacific (Mumbai) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-southeast-6 Asia Pacific (New Zealand) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-northeast-3 Asia Pacific (Osaka) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-northeast-2 Asia Pacific (Seoul) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-southeast-1 Asia Pacific (Singapore) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-southeast-2 Asia Pacific (Sydney) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-east-2 Asia Pacific (Taipei) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ap-southeast-7 Asia Pacific (Thailand) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| us-gov-east-1 AWS GovCloud (US-East) | $0.12 | $0.60 | $0.01 | โ | GovCloud (+20%) |
| ca-central-1 Canada (Central) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| ca-west-1 Canada West (Calgary) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| eu-west-2 Europe (London) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| eu-south-1 Europe (Milan) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| eu-west-3 Europe (Paris) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| eu-south-2 Europe (Spain) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| eu-north-1 Europe (Stockholm) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| eu-central-2 Europe (Zurich) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| il-central-1 Israel (Tel Aviv) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| mx-central-1 Mexico (Central) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| me-south-1 Middle East (Bahrain) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| me-central-1 Middle East (UAE) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| sa-east-1 South America (Sao Paulo) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| us-east-2 US East (Ohio) | $0.10 | $0.50 | $0.01 | โ | Baseline |
| us-west-1 US West (N. California) | $0.10 | $0.50 | $0.01 | โ | Baseline |
No AWS regions found matching your filter.
Developer Quickstart
Invoke Claude Haiku 5.5 via Amazon Bedrock Converse APIPython (boto3) ยท 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-haiku-5-5-v1:0",
messages=[
{
"role": "user",
"content": [{"text": "Summarize key features and cost levers of Claude Haiku 5.5."}]
}
],
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")Compare Claude Haiku 5.5 with Alternatives
Open Multi-Model Estimator →Claude Haiku 5.5 vsJamba 1.5 LargeAI21 Labs
Input Rate:$2.00/1M
Output Rate:$8.00/1M
Claude Haiku 5.5 vsJamba 1.5 MiniAI21 Labs
Input Rate:$0.20/1M
Output Rate:$0.40/1M
Claude Haiku 5.5 vsJamba-InstructAI21 Labs
Input Rate:$0.50/1M
Output Rate:$0.70/1M