This entry is a serving variant of Anthropic: Claude Sonnet 5. A variant shares its base model's tokenizer by construction, so the measurement lives on the base record and this page inherits it.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Not measured | – |
| API surface | Identical contract to 4 other entries | api_051e33bf |
| Context and output | 1,000,000 context · 128,000 max output | declared |
| Reasoning contract | Optional · efforts max, xhigh, high, medium, low · default high | declared |
| Serving providers observed | None recorded yet | – |
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
Supported parameters
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstool_choicetoolsverbosity
defaults: {}
Cite this page as the evidence record for Anthropic: Claude Sonnet 5 (batch): the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.
