OptionalmaxUpper bound on generated tokens.
OptionalreasoningWhether the model can think before it answers.
OptionalparallelWhether the model can ask for more than one tool call in one turn.
OptionalpriceUSD per million input tokens. Needs priceSource.
OptionalpriceUSD per million output tokens. Needs priceSource.
OptionalpriceWhere the prices come from, and when they were checked.
Model id, as the provider names it.
OptionalcontextContext window in tokens, when the provider reports it.
OptionalsupportsWhether the model supports tool calls, when the provider reports it.
A model we know about, with what the provider docs say about it.