---
id: "anthropic/claude-haiku-4.5"
also: ["anthropic/claude-4.5-haiku-20251001", "requesty/anthropic/claude-haiku-4-5", "vercel/anthropic/claude-haiku-4.5"]
card_usd_per_m: "1.0 in, 5.0 out, at anthropic"
cheapest_list_usd_per_m: "1.0 in, 5.0 out, at amazon-bedrock/global on openrouter"
cheapest_effective_usd_per_m: "0.2343 in, 5.4991 out, at amazon-bedrock/eu-west-1 on openrouter"
context: 200000
max_output: 64000
input: ["text", "image", "file"]
output: ["text"]
released: "2025-10-15"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p"]
endpoints: 25
gateways: "requesty (13), openrouter (8), vercel (4)"
no_training: 25
trains: 0
retains_prompts: 3
intelligence: 7.4000
coding: 43.9000
agentic: 8
---
# Anthropic: Claude Haiku 4.5

Claude Haiku 4.5 matches Sonnet 4's performance on coding, computer use, and agent tasks at substantially lower cost and faster speeds. It delivers near-frontier performance and Claude’s unique character at a price point that works for scaled sub-agent deployments, free tier products, and intelligence-sensitive applications with budget constraints.