Skip to main content
veryfront__list_models
Call this before setting model or allowed_models on create_agent, update_agent, or a schedule, and before telling a user a model is unavailable. Use an exact model_id or one of its aliases. Each deployment says where inference is processed (processing: eu, us, worldwide, or unknown; processing_label for display) and who operates it; jurisdiction is the operator’s legal domicile, not the processing location. Prices are per 1M tokens: pricing is what the customer pays, provider_pricing is Veryfront’s upstream cost, and the *_eur_per_1m fields are EUR converted from USD at the top-level fx rate, except provider_pricing on a host that invoices in EUR, which is that host’s published EUR list (the *_usd_per_1m fields are deprecated).

Access

No external-service connection is required. Use a Veryfront credential with access to the requested resources. Call type: Read-only.

Arguments

See the full schema below for the accepted shape and constraints.

Example request

Send this JSON-RPC request through an initialized MCP client. Replace sample identifiers and values before calling the tool. See MCP client setup.
request.json

Result

The published output shape is summarized below. Inspect both the MCP response content and isError when handling a call.

Full schemas