Docs menu · Reference

Decodes an ordered list of token ids back into text using a local model’s vocabulary, returning the reconstructed string. Detokenization is a local-only operation: it requires a build with the local execution feature and returns inference.unsupported_operation for cloud provider specs.

Parameters

NameTypeRequiredDescription
idsinteger[]yesToken ids.
modelstringyesModel spec.

Returns

DetokenizedText.

Errors

Invocation

  • CLI: strata inference detokenize
  • Wire type: inference_detokenize

agents: this page as markdown → /docs/reference/inference/detokenize.md