Anthropic: Claude Haiku 4.5

Text input Image input Text output
Author's Description

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...

Key Specifications
Cost
$$$$
Context
200K
Released
Oct 15, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tools Tool Choice Temperature Include Reasoning Reasoning Max Tokens Structured Outputs Response Format Top P Stop
Features

This model supports the following features:

Structured Outputs Reasoning Response Format Tools
Performance Summary

Claude Haiku 4.5, released by Anthropic on October 15, 2025, demonstrates a strong performance profile, particularly excelling in speed and reliability. It typically performs among the fastest models, ranking in the top tier for speed (70th percentile across 8 benchmarks). While its pricing is moderate (28th percentile), its exceptional reliability is a standout feature, achieving a 100% success rate across all benchmarks with minimal technical failures. The model exhibits near-frontier intelligence across various tasks. It achieved perfect accuracy in both Hallucinations (100%) and Ethics (100%), indicating robust truthfulness and adherence to ethical principles. Its coding capabilities are impressive, scoring 91.0% accuracy, and it performs well in Mathematics (93.0%) and General Knowledge (99.0%). Instruction Following is strong at 70.0% accuracy, and Reasoning is solid at 76.0%. A slight relative weakness is observed in Email Classification, where it scored 97.0% accuracy, placing it in the 41st percentile. Overall, Claude Haiku 4.5 is a highly capable model, offering a compelling balance of speed, accuracy, and reliability for real-time and high-volume applications.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $1
Completion $5
Input Cache Read $0.1
Input Cache Write $1.25
Web Search $10000

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Anthropic
Anthropic | anthropic/claude-4.5-haiku-20251001 200K $1 / 1M tokens $5 / 1M tokens
Google
Google | anthropic/claude-4.5-haiku-20251001 200K $1 / 1M tokens $5 / 1M tokens
Amazon Bedrock
Amazon Bedrock | anthropic/claude-4.5-haiku-20251001 200K $1 / 1M tokens $5 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by anthropic