Expand description
Sending each call to the provider the artifact asked for.
model exact "openai/gpt-5.1" names two things: a vendor and a model. The
model half is the provider’s business; the vendor half decides which
provider, and that decision belongs here rather than in a flag somebody has
to remember.
Deliberately vendor-neutral: this knows about prefixes, not about OpenAI or Anthropic. A backend that adds a third provider registers a prefix and changes nothing else.
Structs§
- Routing
Provider - Dispatches on the
vendor/prefix of a pinned model reference.