The Claude API gives your app Anthropic's Claude models, from Haiku (the cheapest) through Sonnet and Opus to Fable (the most capable). Billing is per million tokens read and written, with lower prices for cached input and half price for batch work that can wait. Our agent-team build pairs a Sonnet or Opus lead with Haiku subagents.
✓Good for
Running several AI agents together on coding or research tasks
Cutting cost by sending simple work to the smallest model
!Watch out for
Costs depend heavily on how many tokens each task uses, so our totals rest on an assumed profile
Small: Haiku 5.5 ($0.10 in / $0.50 out per million tokens, prompts up to 100K). Mid: Sonnet 5.5 ($2 / $10)
The lowest small-model price of the three current-generation models compared here, tied with OpenAI, and half-price batch processing for work that can wait.
Haiku 5.5 costs five times more for prompts over 100,000 tokens ($0.50 in / $2.50 out).