General Questions
What Is Nbility?
Nbility is a unified AI API gateway that lets you access 40+ AI models, including OpenAI, Claude, Gemini, and DeepSeek, with one API Key.
How Compatible Is the API?
Nbility is fully compatible with the OpenAI API format
(/v1/chat/completions). Tools and libraries that support the OpenAI API can
use it directly.
Does It Support Streaming?
Yes. All chat/completions endpoints support the stream: true parameter.
Account and Tokens
What Is the Difference Between a Token and an API Key?
They are the same in Nbility. You can create multiple tokens, and each token can have different quota limits and model permissions.
How Do I Add Balance?
After signing in, open the console top-up page. Recharge codes and online payment are supported.
What Are Groups?
Different groups map to different model sets and pricing multipliers. For
example, the claude group is for Claude models, while the codex group is for
GPT models. See the pricing page for details.
Tool Configuration
How Do I Configure Claude Code?
See the Claude Code setup guide. CC-Switch one-click import is recommended.
How Do I Configure Cursor?
See the Cursor setup guide. Enter the API address and key in Settings -> Models.
Troubleshooting
Requests Return 401
- Check whether the API Key is correct and starts with
sk- - Check whether the token has been disabled
- Check whether the token has enough quota
Requests Return "model not found"
- Confirm that your token group supports the model
- Check the pricing page to confirm the model name
Responses Are Slow
- Different models have different response speeds; Opus models are usually slower
- The first request can be slightly slower because of cold start; later requests are usually faster