Introduction
AI in ARVO Studio can also run on the customer’s own Anthropic account. The account belongs to the customer, the usage sits under their own agreement with Anthropic, and Anthropic bills them directly for what is consumed. This article covers the fields that connect ARVO Studio to that account.
Use this article if you are connecting through Anthropic. If they are using an Azure AI Foundry deployment instead, see Your Azure AI (BYO) article, which is also the single maintained page for the supported model list.
Note: AI runs on the customer’s own Azure AI Foundry deployment or Anthropic account and is paid for by the customer. Bluefort does not resell, supply or absorb AI capacity, and AI usage is not included in the ARVO fee.
Fields
Complete the following on ARVO Studio Setup, in the Anthropic group.
| Field | What to enter | Notes |
| Claude Direct Connection Enabled | Turn on to use the customer’s Anthropic account instead of Foundry | Same rule as Foundry: only one AI connection active at a time. |
| Claude API URL | The standard API endpoint | Change this only if Bluefort Support tells you to. |
| Claude Model | The model identifier for the selected supported model | Take the identifier from the supported-model list in Your Azure AI (BYO), which is the single maintained page for supported models. |
| Claude API Key and Configured | The customer’s API key. Configured confirms that a key is stored. | Write-only. Anthropic bills the customer directly for usage. |
| Claude Max Tokens | Maximum output tokens allowed for one model call | Use the same guidance as the Foundry equivalent: keep the default unless the account enforces a lower limit, because a value that is too low can truncate output and cause validation to fail. |
Only one AI connection at a time
Only one AI connection should be active at a time. If the customer is using their own Anthropic account, enable this connection and leave the Azure AI Foundry connection switched off.
Quick check
Save the group and confirm that Configured shows that a key is stored. Then run Test Connection, which reports whether the selected AI connection responds. If it does not, check the model identifier against the supported-model list in Your Azure AI (BYO) and then re-enter the key. Throughput, throttling, latency and regional availability are controlled by the model provider, not by Bluefort.