Cursor Integration
Point Cursor's plan and agent modes at Claude and GPT models through Halfbill. One base URL override, plus what stays on Cursor's backend.
Cursor is an AI-powered code editor built on VSCode. You can point Cursor's custom OpenAI base URL at Halfbill to use Claude and GPT models in the AI panel — both plan mode and agent mode.
Plan and agent mode. Cursor routes its AI panel — plan mode and agent mode — through the custom API key + base URL, so both work with Halfbill. Tab autocomplete and inline edit (Cmd/Ctrl + K) remain locked to Cursor's own backend and will not route through Halfbill. If you want every request in your workflow to go through Halfbill, use a terminal agent like Claude Code, Codex CLI, Cline, Continue CLI, or Hermes Agent.
Using Halfbill Code? This integration also works with a Halfbill
Code plan key. Use the canonical model IDs from
the catalogue (for example claude-sonnet-5).
Prerequisites
- A Halfbill account with an API key
- Cursor IDE installed
- Basic understanding of Cursor's AI features
Setup
Cursor supports OpenAI-compatible API endpoints, making it easy to integrate with Halfbill.
Get Your API Key
- Log in to your Halfbill dashboard
- Navigate to API Keys section
- Create a new API key and copy the key
Configure Cursor Settings
- Open Cursor and go to Settings then Click on "Cursor Settings"
- Click on "Models"
- Click on "Add OpenAI API Key"

- Scroll down to OpenAI API Key section
- Click on Add OpenAI API Key

-
Enter your Halfbill API key
-
In the same Models settings, find the Override OpenAI Base URL option
-
Enable the override option
-
Enter the Halfbill endpoint:
https://api.halfbill.uk/v1
Select Models
- In the Models section, you can now select from available models
- Choose any Halfbill supported model:
- For chat and agent tasks: use models like
gpt-5.5,claude-sonnet-5,claude-opus-5 - Copy exact model IDs from the models page
Test the Integration
- Open any code file in Cursor
- Try using the AI chat (Cmd/Ctrl + L) in plan mode
- Then switch the panel to agent mode and run a small multi-file task

All AI requests will now be routed through Halfbill.
What Works (and What Doesn't)
Cursor honors the custom OpenAI base URL for the AI panel (Cmd/Ctrl + L) — both plan mode and agent mode. Tab autocomplete and inline edit still use Cursor's own backend, even after you save the Halfbill key.
Works through Halfbill
- Plan mode (Cmd/Ctrl + L) — Ask questions, plan changes, get explanations, debug.
- Agent mode — Cursor's coding agent runs multi-file edits with your Halfbill models.
All of these requests route through Halfbill and appear in your dashboard.
Does NOT work through Halfbill
- Inline Edit (Cmd/Ctrl + K) — Locked to Cursor's backend.
- Autocomplete / Tab completion — Locked to Cursor's backend.
If you want every request in your workflow — including edits and completions — to route through Halfbill, use Claude Code, Codex CLI, Cline, Continue CLI, or Hermes Agent.
Troubleshooting
Authentication Errors
If you see authentication errors:
- Verify your API key is correct
- Check that the base URL is set to
https://api.halfbill.uk/v1 - Ensure your Halfbill account has sufficient credits
Model Not Found
If you see "model not found" errors:
- Verify the model ID exists in the models page
- Check that you're using the exact model ID, without any prefix
Slow Responses
If responses are slow:
- Check your internet connection
- Monitor your usage in the Halfbill dashboard
- Switch to a faster model such as
claude-haiku-4-5from the models page
Autocomplete / inline edit still uses Cursor's models
This is expected. Cursor routes the AI panel — plan mode and agent mode — through the custom API key, but tab autocomplete and inline edit are locked to Cursor's own backend. See What Works (and What Doesn't) above.
Need help? Email support@halfbill.uk.
Benefits of Using Halfbill with Cursor
- Claude and GPT in one place: Use models from Anthropic and OpenAI with a single key
- Cost Control: Track and limit your AI spending with detailed usage analytics
- Caching: Reduce costs with response caching
- Analytics: Monitor usage patterns and costs
How is this guide?