Claude Haiku 4.5

Claude Haiku 4.5 is designed as a lightweight, high-performance model that prioritizes speed and efficiency without sacrificing intelligence. It serves as an accessible entry point for users who require rapid, accurate responses for real-time applications, such as customer service agents, chat assistants, and pair programming. By balancing a compact architecture with significant reasoning capabilities, the model is specifically optimized to handle complex, real-world coding tasks and agentic workflows, making it a versatile tool for developers and enterprise users alike.

Built to provide near-frontier performance at a fraction of the cost of larger models, Claude Haiku 4.5 demonstrates significant advancements in practical utility, including a 73.3% score on SWE-bench Verified. Its design lineage emphasizes responsiveness, allowing it to outperform previous-generation models in specialized areas like computer use. With support for extended thinking, the model is well-suited for multi-agent projects and rapid prototyping, offering a responsive experience that integrates seamlessly into modern development environments like Claude Code.

Vertex (Anthropic)claude-haiku-4-5@20251001claude-haiku

Open provider page Provider docs

Quick Info

Provider: Vertex (Anthropic)
Model key: claude-haiku-4-5@20251001
Release date: Oct 15, 2025
Last updated: Oct 15, 2025
Knowledge cutoff: 2025-02-28
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $1.00
Output token cost: $5.00

Limits

Output tokens: 64,000 tokens
Context window: 200,000 tokens

Transparent token rates

Compare Claude Haiku 4.5 pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Claude Haiku 4.5

Vertex (Anthropic)

CoverageBenchmark

The n8n AI benchmark page profiles Claude Haiku 4.5 as Anthropic's fastest and most efficient model, positioned for real-time and high-volume applications. It lists a 200,000 token context window with up to 5 token max completion (as displayed), text and image input support, and pricing of $1 per million input tokens a Benchmark placement on n8n shows Haiku 4.5 at an overall score of 80 (5th placement), with category scores including Cost 87, Logic 77, Speed 93, Tool Use 51, Hallucination 97, Classification 50, and Structured Output 92. The model scores 73% on SWE-bench Verified and ranks just behind GPT-5.1 and GPT-5.1-Codex among 5

Vertex (Anthropic)

CoverageComparison

GPT-5.4 Mini is cheaper and faster than Claude Haiku 4.5 with better benchmarks. Compare both models for sub-agent use cases and token efficiency.

Vertex (Anthropic)

CoverageBenchmark

Claude Haiku 4.5 delivers near-frontier AI performance at baseline cost. Read on to find full benchmark analysis, feature breakdown, and how to get started.