Expand description
Token limits of one upstream model.
ModelLimits is the per-model ceiling a codec clamps a request to: the
context window, the output-token cap and the optional thinking budget. The
provider catalog carries one per model; the codecs read it when they render
an upstream request.
Copyright (c) systemprompt.io — Business Source License 1.1. See https://systemprompt.io for licensing details.