← Back to Calculator

Claude Fable 5 vs Claude Haiku 4.5

Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-06-29.

Cost at a Glance

Claude Fable 5 is 10× more expensive than Claude Haiku 4.5 — switching could save 90% on your monthly API bill.

At 5M input + 2M output tokens per month:

Claude Fable 5$150.00/movsClaude Haiku 4.5$15.00/mo

Choosing Claude Haiku 4.5 could save you $135.00/mo

Price Comparison (per 1M tokens)

Input (per 1M tokens)
$10.00vs$1.00
Output (per 1M tokens)
$50.00vs$5.00
Cache Write (per 1M tokens)
$12.50vs$1.25
Cache Read (per 1M tokens)
$1.00vs$0.10
Batch Input (per 1M tokens)
$5.00vs$0.50
Batch Output (per 1M tokens)
$25.00vs$2.50

Prices are per 1 million tokens. Actual costs depend on your monthly token volume. Use the calculator →

Specifications

Context Window
1Mvs1M
Max Output Tokens
128Kvs64K
Knowledge Cutoff
2026-04vs2026-03
Modalities
Text, ImagevsText, Image
Prompt Caching
YesvsYes
Batch API
YesvsYes
Thinking / Reasoning
YesvsNo

Benchmark Scores

SWE-bench Verified
88.7vs55.3
MMLU-Pro
88.5vs76.8
HumanEval
96.3vs88.2

Benchmark scores from official provider reports. Higher is better. Missing scores indicate the provider has not published that benchmark yet.

Use Cases

Claude Fable 5

reasoningcodinganalysispremium

Claude Haiku 4.5

fastcheapgeneral

About the Providers

Claude Fable 5 is developed by Anthropic. Claude Haiku 4.5 is developed by Anthropic. Both models are from the same provider, representing different tiers in the Anthropic model lineup. For the most up-to-date pricing, always check the official API documentation from each provider.

Compare More AI Models