Status and lifecycle
Which models are active and which are deprecated, with request volume per model over time.
Loading
Model gateway
The gateway is where your organization decides which models exist. Models are added, approved, routed to and eventually deprecated — without your teams changing how they work, and without your platform being tied to one provider.
What you control
Which models are active and which are deprecated, with request volume per model over time.
Cost per million tokens in and out, visible against usage so spend is a governed number rather than a surprise.
The registered set of work AI may do in a workspace — code generation, review, test generation, security review, refactoring, bug fixing, documentation, general assistance — each with its own permitted models.
Self-host open-weight models entirely inside your boundary, or route to external providers where policy allows. Swapping a model is a configuration change, not a migration.
Next step
Request a demo based on your use case, deployment environment and governance requirements.