Anthropic
Haiku 4.5
A fast, cost-efficient Claude model for everyday chat, drafting, and lighter coding tasks. It supports text, images, and direct document input, but runs without adaptive thinking so it stays focused on speed and cost efficiency.
Quick facts
Pricing
Input $1 / Output $5 per 1M tokens
Context window
200K
Max output
64K
Knowledge cutoff
2025-07
What this model can do
You provide
- 📄 Documents (PDFs, Word, TXT)
- 🖼️ Images & Screenshots
- 💬 Text instructions
It creates
- 📝 Formatted text & summaries
- 📊 Excel sheets & CSV data
- 📽️ PowerPoint slides & decks
- 💻 Usable code snippets
- 🎨 Generated images
Capabilities
Reasoning
Optimized more for speed and straightforward tasks than deep reasoning.
Vision
Can work with screenshots, charts, or other image inputs.
Document input
Can accept supported documents directly in chat.
Structured output
Primarily aimed at natural-language output.
Tool use
Can use compatible tools when crowSync enables them for the run.
Native tools in crowSync
Web search
Search the live web during a run.
Available
Web fetch
Open and read webpage contents directly.
Available
Code interpreter
Run code for calculations, analysis, and generated files.
Available
Image generation
Generate images directly from prompts.
Available
Input and output
Input
- Text
- Image
- Documents
Output
- Text
Common use cases
- Fast everyday chat, drafting, and lightweight help.
- Research tasks that need current information from the web.
- Summarizing PDFs, documents, or longer working files.
- Data analysis, calculations, and code-backed workflows.
Pricing details
Input
$1 / 1M tokens
Output
$5 / 1M tokens
Cached input
$0.10 / 1M tokens