LLM Providers - 2501.ai

Models and providers are managed per tenant in a catalog in Command Center. Configure the providers and models your agents will use; the on-premise installer and 2501 infra deploy do not populate this catalog from environment API keys. Contact your Account Executive at 2501 for the complete list of supported providers and models.

Providers and models

Create providers in Settings > Providers, attach their credentials, then create models in Settings > Models. You can configure custom or Azure endpoints, enable or disable providers and models, set model pricing, and run model performance tests without restarting the engine. See Providers and Models for the full catalog reference.

Existing model configurations are preserved on upgrade. Per-provider feature toggles have been removed; whether a provider or model is available is now controlled by its Enabled toggle in the catalog.

Setting Tenant Models

Choose the tenant defaults in Settings > Tenant from the configured model catalog. For initial tenant setup, tenant.yaml can also carry default model keys:

tenant:
  name: My Company
  llm_model: "<your-llm-model>"
  multimodal_llm_model: "<your-multimodal-model>"
  timezone: Europe/Paris

These values name model keys; they do not create provider or model entries. Configure the corresponding catalog entries before using the defaults. You can change the defaults later in Settings > Tenant.