• Home
  • Search
  • AI Services
  • Models
  • Writing
  • Multimedia Creation
  • Translation & Others

Anthropic Claude Haiku 4.5

Anthropic Claude Haiku 4.5, the fastest and cheapest Claude model.

Anthropic Claude Haiku 4.5, the fastest and cheapest Claude model. Strong for classification, extraction, routing, and short-form chat. Use it for high-volume workflows where latency and cost matter more than top-end reasoning. If you need to search the web for information, please turn on the "Web Search" switch. Prompt example 1: Translate this into Chinese: Your package was shipped this morning and should arrive within two days. Prompt example 2: Write a friendly customer service auto-reply, in three sentences or fewer, for customers asking how to change the delivery address on an order. Prompt example 3: Decide whether this comment contains ads or inappropriate content. Answer only Pass or Fail with a one-line reason: DM me for a mystery gift, only for three days! Prompt example 4: Sum up this support chat in three points for the next agent: Customer: My kettle won't turn on. Agent: Please check the plug. Customer: A new outlet didn't help; it's two weeks old, I want a new one. Prompt example 5: Write a warm, professional Thanksgiving greeting message of under 30 words for our business clients. Prompt example 6: Decide whether this message should go to a human agent, answering only Yes or No: I have restarted it three times like you said and it still fails, can someone help me? Prompt example 7: Rewrite this product name into a short, catchy version of under 8 words: Ultra Light Foldable Multi-Function Stainless Steel Hot and Cold Travel Tumbler Large 600ml Prompt example 8: Explain to a primary school student in three sentences why we have seasons. Prompt example 9: Our online meeting is at 3 p.m. Taipei time on November 20. What local time is that for my colleagues in London and New York? Prompt example 10: A customer types I forgot my password. Give three quick-reply button labels for the chatbot, each under four words. Maximum context window (input and output combined): about 200,000 tokens. Maximum output per reply: about 64,000 tokens (model reasoning, if any, counts toward this limit). Maximum total upload size per request: 512MB (all files and message content combined). Accepted document formats: pdf, docx, xlsx, pptx, txt, csv (file content is provided to the model as extracted text). Accepted image formats: gif, jpeg, jpg, png, webp. Animated GIF images are analyzed using only the first frame. Maximum number of images: 100. When uploading more than 20 images, each side must be at most 2,000 pixels. Maximum size per image: 10MB (base64-encoded). Maximum total image size per message: 20MB (text and history share the same request size limit; uploads close to the limit may still be rejected). Image dimensions: 200 to 8,000 pixels per side. Output content formats: Text/Image Pricing: Medium Continuous conversation: Supported AI can make mistakes. Please verify important information.