Back to Models

Claude haiku 4.5

Claude Haiku 4.5 is Anthropic's fastest and most cost-effective model, featuring a 200K context window. It delivers near-frontier reasoning and coding speeds suitable for real-time agentic applications.

Thinking Mode
Parameters
N/A
Context
200,000 tokens
Released
Invalid Date

Leaderboards

Average Score combining domain-specific Autobench scores; Higher is better

Performance vs. Industry Average

Intelligence

Claude haiku 4.5 is of higher intelligence compared to average (2.9), with an intelligence score of 3.0.

Price

Claude haiku 4.5 is more expensive compared to average ($0.75 per 1M Tokens) with a price of $0.84 per 1M Tokens.

Latency

Claude haiku 4.5 has a lower average latency compared to average (44.25s), with an average latency of 43.07s.

P99 Latency

Claude haiku 4.5 has a higher P99 latency compared to average (126.46s), taking 151.05s to receive the first token at P99 (TTFT).

Context Window

Claude haiku 4.5 has a smaller context window than average (406k tokens), with a context window of 200k tokens.

Claude haiku 4.5 - AutoBench