SillyTavern
Connect SillyTavern's custom OpenAI-compatible source to Gondola and reach any Venice model, paid per request in USDC on Base.
Create an API key
Point SillyTavern at Gondola
Open the API Connections panel, set the API type to chat completion, and choose the custom OpenAI-compatible source. Enter the Gondola endpoint and your gnd_ key, then connect. The model dropdown fills in automatically from Gondola's catalog. Turn on the streaming option in the response settings for token-by-token replies.
Pick a model
Because the model list is fetched from Gondola, you can usually pick from the dropdown. To see the exact ids (and confirm one is available) pull the live list:
Example ids today include claude-sonnet-5 and qwen3-coder-480b-a35b-instruct-turbo, but always confirm against the live list, since the catalog changes. Each entry reports context_length, which you can use if you unlock the context size manually.
Notes and troubleshooting
If the connection is flagged as down but works, toggle the option to bypass the status check and verify with a test message. If a request returns insufficient balance, top up at /wallet.