Claude Haiku 4.5 Thinking
Fast Claude model for responsive assistance, classification, and lightweight agents
Model facts
- Context window
- 2K tokens
- Maximum output
- 64K tokens
- Cheapest paid input
- $1 per 1M tokens
- Cheapest paid output
- $5 per 1M tokens
- Open weights
- no
- Providers
- 1
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, text, image, pdf.
Observed price history
- 2026-08-24: $1 input / $5 output per 1M tokens
API providers
- NanoGPT — model id claude-haiku-4-5-20251001-thinking; $1 input / $5 output per 1M tokens; provider documentation