ModelsCompareBest forBenchmarksStatusPricingAPI

Claude Haiku 4.5

Anthropic·Operational·Released 2025-10-15textvision
Context200k
Max output64k
Input / 1M$1 ↗
Output / 1M$5 ↗
Cached in$0.1
Benchmarks4

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

GPQA Diamond (Epoch AI run)#64/7771.2% ↗
OTIS Mock AIME 2024-2025 (Epoch AI run)#61/7666.7% ↗
SimpleQA Verified (Epoch AI run)#48/5313.2% ↗
SWE-bench Verified#22/4573.3% ↗

Compare

vs GPT-6 Astravs GPT-5.6 Solvs GPT-5.6 Terravs GPT-5.6 Lunavs Claude Fable 5.1vs Claude Opus 5vs Claude Sonnet 5vs Gemini 3.8 Flash

More from Anthropic

Claude Fable 5.1Claude Opus 5Claude Sonnet 5Claude Opus 4.8Claude Opus 4.7Claude Opus 4.6

Access Claude Haiku 4.5 and every other model through one endpoint with automatic failover: Respan gateway.