Claude Haiku 4.5

Anthropic · Released Oct 1, 2025

Input price / MTok

Output price / MTok

200K

Context window

Tokens / sec

73.3

SWE-bench Verified

80.7

AIME 2025

73.2

MMMU

50.7

OSWorld

Summary

Claude Haiku 4.5 is a proprietary language model from Anthropic, released on Oct 1, 2025.

At $1 input and $5 output per million tokens, it ranks #15 of 40 for input price, placing it mid-range on input cost.

Its context window of 200K tokens ranks #35 of 41 for context depth in this dataset.

It targets budget, agents workloads.

Throughput is measured at 98 tokens per second (ranked #13 of 23 for throughput).

Fastest Claude model; best for high-volume and real-time tasks.

Benchmarks

Technical specs

Anthropic

Similar Models

Models with the most shared benchmark coverage and closest scores to Claude Haiku 4.5.

Compare Claude Haiku 4.5 side by side

Pre-filled with 5 similar models

Speed source: https://artificialanalysis.ai/models/claude-4-5-haiku