Compare / Claude models

Anthropic ยท as of November 12, 2026

Which Claude model for which job

The prices side by side, and what Anthropic itself says about where to start. These are API prices per million tokens, not what a Claude app user pays.

The prices

ModelInputOutputNote
Claude Haiku 5.5from $0.10from $0.50Anthropic lists these as starting prices.
Claude Sonnet 5.5$2$10The base of the doubling ladder.
Claude Opus 5.5$4$20Anthropic: "our strongest daily driver", and where to start for most work.
Claude Fable 5.2$8$40For demanding reasoning and long-horizon agentic work.

From Sonnet 5.5 up, each model costs double the one below, for input and output. That ladder does not include Haiku.

Where to start

  • Anthropic recommends most users start with Claude Opus 5.5, “our strongest daily driver”, then move up to Fable or Mythos, or down to Sonnet 5.5 or Haiku 5.5, depending on the scope and complexity of the work. Anthropic says, for most coding and knowledge work.
  • Anthropic’s models docs say: if you are unsure which model to use, start with Claude Opus 5.5 for most workloads, and use Claude Fable 5.2 for demanding reasoning and long-horizon agentic work, or when your evals on Opus 5.5 at higher effort still fall short.
  • Fable 5.2 generates output up to 30% faster than Fable 5.1, at a lower price.

Sources

Prices change. Check Anthropic’s pages before you plan a budget around them.

More comparisons, by email