Retrieve model
Retrieves a model by ID or name. OpenAI-compatible.
Path Parameters
Model ID (UUID) or name
Query Parameters
Pass "live" to refresh deployment status from provider before responding
live Response
Model details
Represents a model available for inference or fine-tuning. Compatible with the OpenAI model object.
Unix timestamp when the model was registered
Model identifier used in API calls
model "oxen" for base models, owner namespace for custom models
Provider-documented context window: total tokens the model can attend to. Null for models without a documented window (e.g. image/video models).
Active deployments. Empty for base models.
API endpoint to call this model
/chat/completions, /images/generate, /videos/generate Fine-tuning info, or null if model is not fine-tuneable
Maximum tokens a single completion can produce. Null when the provider does not document a cap.
base, custom JSON Schema describing model-specific parameters
Optional marketing content rendered on the public model showcase page
Base model this was fine-tuned from