Cline
Add Gondola as an OpenAI Compatible provider in Cline and run any Venice model, paid per request in USDC on Base.
Create an API key
Point Cline at Gondola
Open the Cline settings (the gear icon in the Cline panel) and set the API Provider to OpenAI Compatible. Fill in the Base URL, API Key, and Model fields. Paste the key raw, with no Bearer prefix (Cline adds it).
In the Model Configuration section, set a real Context Window and Max Output Tokens (see step 3 for where the numbers come from), and enable Computer Use if you want Cline to take agentic actions.
Pick a model
Gondola serves the full Venice catalog. Model ids must be typed exactly as the catalog lists them, so pull the live list:
Each entry includes context_length and max_completion_tokens. Copy those into Cline's Context Window and Max Output Tokens fields. 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.
Notes and troubleshooting
The Input Price and Output Price fields are display-only cost estimates (dollars per million tokens). They do not change what you are billed; the real price is the live marketplace rate. If a request returns insufficient balance, top up at /wallet.