← Back to Model Hub/SIDE-BY-SIDE REVIEW
SHARE THIS:

Claude Fable 5 vs Claude Haiku 4.5

How do these models stack up? Below is an expert side-by-side comparison of specifications, context window capacity, live pricing per million tokens, and standardized benchmark scores for Claude Fable 5 and Claude Haiku 4.5.

Anthropic

Claude Fable 5

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

View Full Specs
Anthropic

Claude Haiku 4.5

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

View Full Specs

Technical Specifications

SpecificationClaude Fable 5Claude Haiku 4.5
ProviderAnthropicAnthropic
Context Window1,000,000 tokens200,000 tokens
Agent SuitabilityN/A87/100
Time to First Token (TTFT)N/A180 ms
Deployment Modelmanaged apimanaged api
Production Stabilitybetastable
API AvailableYesYes
Released Date2026-06-092025-10-15

API Pricing Comparison

Input Price per Million Tokens

Claude Fable 5

$10.00

Claude Haiku 4.5

$1.00

Output Price per Million Tokens

Claude Fable 5

$50.00

Claude Haiku 4.5

$5.00

Want to test both models live?

Run side-by-side prompt prompts in our dynamic Sandbox. Check execution speeds, latency metrics, and compute actual costs in real-time.

Benchmark Performance Metrics

Scores show the raw performance percentages verified across key evaluation suites. Higher bars indicate superior accuracy and capability in that domain.

MMLUGeneral knowledge & multi-task understanding
N/Avs8480.0%
Claude Fable 5
Claude Haiku 4.5
HumanEvalPython coding & logic synthesis
N/Avs8600.0%
Claude Fable 5
Claude Haiku 4.5
MATHComplex mathematical problem solving
N/Avs7500.0%
Claude Fable 5
Claude Haiku 4.5
GPQAGraduate-level expert reasoning
N/Avs5500.0%
Claude Fable 5
Claude Haiku 4.5
HellaSwagCommonsense reasoning and inference
N/Avs9350.0%
Claude Fable 5
Claude Haiku 4.5
MT-BenchMulti-turn conversation flow quality
N/Avs890.0%
Claude Fable 5
Claude Haiku 4.5

Claude Fable 5 Quirks & Gotchas

No developer gotchas reported.

Claude Haiku 4.5 Quirks & Gotchas

  • Fastest TTFT in the Claude lineup — ideal for real-time chat
  • Tool calling limited compared to Sonnet — best for simple classification and routing