Claude Haiku 4.5 (batch)

ANTHROPIC Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1423Chatbot Arena Verified

Max Context Limit200,000Max Out: 64,000 tokens

Prompt Caching90% OFF$0.05 / 1M cached

Standard API / 1M$3.00Blended Standard Rate

Model Capabilities & Contract SLAs

Drafting
Classification
Agentic
Coding & Logic
Fictional
📋 Strict JSON Schema
🛠️ Native Tool Calling

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...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.50 / 1M

⚡ Cached Input (Prompt Cache Read)90% OFF$0.05 / 1M

Output Tokens (Completion)$2.50 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupClaude Haiku 4.5 (batch) vs Qwen: Qwen3.5 Plus 2026-04-20 VS Engine MatchupClaude Haiku 4.5 (batch) vs Qwen: Qwen3.5 Plus 2026-02-15 VS Engine MatchupClaude Haiku 4.5 (batch) vs Relace: Relace Apply 3 VS Engine MatchupClaude Haiku 4.5 (batch) vs Qwen: Qwen3 Next 80B A3B Thinking VS Engine MatchupClaude Haiku 4.5 (batch) vs Mistral: Mistral Medium 3 VS Engine MatchupClaude Haiku 4.5 (batch) vs Meta: Llama 4 Maverick