These examples use the direct API host,
https://api.nano-gpt.com. It has no IPv6 address, so clients with only IPv6 should use https://nano-gpt.com with the same paths. See API Hosts.Using Cline with NanoGPT
A quick guide to setting up Cline with NanoGPT’s API.Setup Instructions
- Get your API key from nano-gpt.com/api
- In Cline settings, add a new Custom Model with these details:
- API Provider: OpenAI Compatible
- Base URL: https://api.nano-gpt.com/api/v1/
- API Key: Your key from step 1
- Model ID: openai/gpt-6.1-sol
Tip: If Cline is not showing a model’sthinkingoutput, switch the Base URL tohttps://api.nano-gpt.com/api/v1legacy/. Cline still expects the legacy streaming shape for parallel thinking/output channels, and this endpoint keeps that compatibility without affecting model availability. It only changes the response shape; it doesn’t turn reasoning on for a model.
Subscribers
With the Base URL above, Cline lists every NanoGPT model, including models your subscription doesn’t cover. To see only the models your subscription includes, usehttps://api.nano-gpt.com/api/subscription/v1/ as the Base URL instead: Cline then loads its model list from /api/subscription/v1/models. The subscription Base URL has no v1legacy variant, so the thinking tip above doesn’t apply to it. To keep a key from ever billing your balance, set its billing mode to Subscription only (see API key billing settings); requests your subscription doesn’t cover are then rejected instead of charged.
That’s it! You can now use Cline with every model you can think of. Model names are on our pricing page - important ones are openai/gpt-6.1-sol, anthropic/claude-opus-5.5, google/gemini-flash-latest, or just any other model you fancy.