Claude Haiku 4.5
Anthropic
anthropic/claude-haiku-4-5
Ultra-fast, lowest cost
Context Window
200K
200,000 tokens
Max Output
8K
8,192 tokens
About this model
Claude Haiku 4.5 is the fastest and cheapest model in the Claude series. Designed for real-time applications requiring fast responses, it excels at simple to moderately complex tasks.
Input pricing at just $1.05/M tokens, 1/3 of Sonnet. Supports 200K context and vision understanding. Prompt Caching further reduces costs for repetitive requests.
Best suited for high-throughput batch processing and latency-sensitive applications.
Highlights
1/3 price of Sonnet
Ultra-low latency
200K context
Vision support
Best For
Real-time chatbotsBatch text processingClassification & labelingContent moderation
2025-10-22TransformerProprietary
Capabilities
ChatVisionReasoningCodepdftoolscache
Aliases
claude-haiku-4-5claude-haikuhaikuhaiku-4haiku-4-5Pricing (per 1M tokens)
| Pricing (per 1M tokens) | / 1M tokens |
|---|---|
| Input / 1M | $1.05 |
| Output / 1M | $5.25 |
| Cache Read | $0.10 |
| Cache Write | $1.31 |
Final prices shown
Quick Start
main.py
import anthropic client = anthropic.Anthropic( base_url="https://api.chuizi.ai/anthropic", api_key="ck-your-key-here", ) message = client.messages.create( model="claude-haiku-4-5-20251001", max_tokens=1024, messages=[{"role": "user", "content": "Hello!"}] ) print(message.content[0].text)