Getting started Community Training Tutorials Documentation APIs, AI & Tools
-
API Manager: API Creator
-
API Manager: View APIs Configuration
-
API Manager: Manage APIs Configuration
Set a cost for each model so usage translates into spend tracking. The Models page lists the AI models available in your organization. Wallet budgets can cap spend or token count. Spend caps use the model costs that you set here.
To set model costs, you need:
An Anypoint Platform account.
API Manager permissions:
API Manager: API Creator
API Manager: View APIs Configuration
API Manager: Manage APIs Configuration
API Manager permissions apply to individual environments. Grant permissions in each environment where you need them.
For more information, see Agent Fabric Permissions.
The Models page lists available models, the proxies that use them, and any costs you have set.
From Portfolio > Model Proxies, select Models.
Review the list of available models.
To see details for a model, select its name.
The model detail page shows the model proxies that use the model and the model’s configured costs if applicable.
Model costs drive spend and budget calculations. Set a cost per token for each model that you use.
From Portfolio > Model Proxies, select Models.
Select a model, for example, Claude 3.5 Haiku.
Select Edit from the Actions menu.
Enter the Cost per 1M Input Tokens, for example, 0.01.
Enter the Cost per 1M Output Tokens, for example, 0.05.
Select Save changes.
If a model has no configured cost, then spend tracking and spend-based wallet budgets treat that model’s usage as zero. Token-based wallet budgets still count tokens. See Cap Spend for Callers of Model Proxies.
|
You can set a wallet budget as a dollar amount or as a token count. A model without a configured cost is still blocked when a token-count budget limit is reached. The model proxy counts that model’s tokens and blocks further requests when usage reaches the token limit. That block is based on token usage, not dollar spend. Spend tracking and a dollar budget treat usage of a model with no configured cost as zero, so a dollar spend limit does not apply. To cap the model by dollar spend, set the cost per token for the model first. See Cap Spend for Callers of Model Proxies. |