GET /platform/v2/models endpoint — so it always reflects the current platform catalog. Use the Model ID column as the model parameter in your requests.
The rates shown are list prices (each model’s base rate). Usage is billed at the list rate plus a flat platform rate. Track real spend in the Gloo Studio billing dashboard.
Model routing. Gloo AI routes requests to the right provider automatically, with built-in resilience so traffic keeps flowing even if a provider has an issue. Routing is invisible to you and does not change a model’s price — the platform rate stays consistent regardless of how a request is served.
These model IDs work across both the Responses API (
/ai/v2/responses — the recommended surface for new integrations) and Completions V2 (/ai/v2/chat/completions). Per-model capability flags (supports_tools, supports_streaming, supports_reasoning, supports_vision) are shown in the Model Capabilities table at the bottom and are also available programmatically on the GET /platform/v2/models response.Deprecated Models
Models being retired are flagged live in the catalog table below: a deprecated model renders a Deprecated badge next to its ID, with its deprecation note inline. Those come from theis_deprecated and deprecation_note fields on GET /platform/v2/models, alongside replacement_model — the ID that requests are routed to.
Where a replacement has been chosen, a deprecated model keeps working while you migrate: its requests are routed to that replacement, so the flag appearing is not itself a breaking event. Read deprecation_note for the specifics — it is where a price change, or the absence of a replacement, is stated. New integrations should target the replacement ID directly.
See Model Lifecycle for how a replacement is chosen, what the price can do, how much notice you get, and how to detect all of it from the API.