Skip to content
CortexDocs

Choose a model

Choose an organization-enabled model and understand its API token rates.

The model catalog in Cortex updates daily with model IDs and default provider API prices.

Find a model

Open Model catalog in Cortex. Search by model name, exact ID or provider, then use an exact ID enabled for your organization.

Model catalog with provider configuration, base token rates, search and provider filtersOpen in Cortex

Provider configuration does not confirm model access. Verify access with a request through your gateway.

Egress Gateway also supports open-weight and self-hosted models through a compatible endpoint. See Providers and cloud platforms.

Which prices apply?

The catalog shows default API prices in USD per million tokens. These are usage rates, not per-seat fees or subscriptions such as Claude Max.

Cortex uses default API rates to estimate spend unless your organization has configured custom rates, such as negotiated provider pricing.

For current provider pricing, see OpenAI, Anthropic, and Google Gemini. Caching, service tiers and tool charges can affect the final bill.

For a breakdown of captured usage, see AI spend.