Claude Haiku 4.5

Claude Haiku 4.5 is Anthropic's fast lane model for lightweight agents, office tasks, and responsive chat. It is the first version of the claude-haiku line in the registry, released on 2025-10-15. It has a 200,000 token context window and a 64,000 token maximum output. Pricing starts at $0.14 per million input tokens and $0.71 per million output tokens, with cached input at $0.06 per million tokens. Weights are not open. It supports reasoning mode, tool calling, accepts image, pdf, and text inputs, and returns text. Knowledge cutoff is 2025-02-28. It is served by 30 hosts.

First version of its line in the registry.

Range across the hosts that serve it: up to $1.20 per 1M input tokens.

• ·200k token context window
• ·64k token max output
• ·Supports reasoning mode and tool calling
• ·Accepts image, pdf, and text inputs
• ·Cached input at $0.06 per million tokens

• Reach for it for lightweight agent tasks
• Reach for it for office document processing
• Reach for it for responsive chat applications
• Reach for it for tasks needing image or pdf input

30 hosts serve this model at the price above · the maker's documentation

• 8Show HN: Rules that stop AI agents from wrecking your warehouse, with an eval2026-09-30

1 signal of the archive mention this model, each scored against the published bar. This list is rebuilt from the archive at every build, so it cannot go stale.

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window and output limit?

The context window is 200,000 tokens and the maximum output is 64,000 tokens.

What are the input and output prices?

Input starts at $0.14 per million tokens, output at $0.71 per million tokens. Cached input is $0.06 per million tokens.

Does it support tool calling and reasoning?

Yes, it supports both reasoning mode and tool calling. It also accepts image, pdf, and text inputs.