model parameter. The List models endpoint returns the models you can use, which can differ between organizations and plans, and Retrieve a model returns one of them.
Beam supports reasoning, tool calling, and structured outputs.
List models
Response
default_parameters and reasoning.default_effort can differ between organizations, so yours reports the values that apply to your organization.
Each model object has these fields:
The Unix time, in seconds, when the model was published, or
0 if its publication time isn’t announced.The largest request the model supports, in tokens, counting the prompt and the generated output together. Omitted if not announced.
The most tokens the model supports generating in response to one request. Omitted if not announced.
The settings the model applies to your organization’s requests. See Default parameters. Omitted if the model sets none.
The model’s reasoning efforts: the
reasoning_effort values it accepts, the effort it applies when your organization’s request omits one, and whether reasoning is always on. Omitted if not announced.The largest
top_logprobs a chat completion request for the model accepts. Omitted if the model doesn’t return log probabilities.restricted when your account can call the model, or see it listed, through access not all accounts have, such as early access. Omitted when all accounts have that access; its absence says nothing more. The value describes your account at the time of the request, and can differ between accounts or change. More values may be added; read one you don’t recognize as saying nothing.Default parameters
default_parameters lists the settings the model applies to your organization’s chat completion requests. They can differ between organizations, and settings that aren’t listed use the model’s own defaults.
Retrieve a model
To get one model, request it by ID. The response is a single model object with the same fields, and an unknown or unavailable model returns404 with code model_not_found.
Model lifecycle
When a model is scheduled to shut down, itsshutdown_date is set. Plan to move to another model before that date; requests that name a model that no longer exists return 404.
To detect upcoming shutdowns automatically, check shutdown_date on the models you use, for example at application startup or in a scheduled job.