Continue CLI Integration

Point Continue CLI at Claude and GPT models through Halfbill. One config file, unified billing, full cost tracking.

Continue is an open-source AI code assistant available as a CLI tool. By configuring it to use Halfbill, you get Claude and GPT models with unified cost tracking.

One config file. Any Halfbill model. Full cost visibility.

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 API key — sign up

Setup

Install Continue CLI

Install Continue CLI globally:

npm install -g @continuedev/cli

Get Your API Key

Sign up or log in to your Halfbill dashboard. Navigate to API Keys and create a new key. Copy it — it starts with llmgtwy_.

Create a Config File

Create the Continue config directory and config file:

mkdir -p ~/.continue

Then create ~/.continue/config.yaml with your Halfbill configuration:

name: halfbill
version: 0.0.1
models:
  - name: claude-sonnet-5
    provider: openai
    model: claude-sonnet-5
    apiBase: https://api.halfbill.uk/v1
    apiKey: llmgtwy_your-api-key-here

Replace llmgtwy_your-api-key-here with your actual API key from the dashboard.

Add More Models (Optional)

Add as many models as you want from the models page:

name: halfbill
version: 0.0.1
models:
  - name: claude-sonnet-5
    provider: openai
    model: claude-sonnet-5
    apiBase: https://api.halfbill.uk/v1
    apiKey: llmgtwy_your-api-key-here
  - name: gpt-5.5
    provider: openai
    model: gpt-5.5
    apiBase: https://api.halfbill.uk/v1
    apiKey: llmgtwy_your-api-key-here
  - name: claude-opus-5
    provider: openai
    model: claude-opus-5
    apiBase: https://api.halfbill.uk/v1
    apiKey: llmgtwy_your-api-key-here

All models use provider: openai since Halfbill exposes an OpenAI-compatible API.

Start Using Continue

Launch Continue CLI with the --config flag pointing to your config file:

cn --config ~/.continue/config.yaml

All requests now route through Halfbill. You'll see usage, costs, and logs in your dashboard.

Why Use Halfbill with Continue

Claude and GPT — Anthropic and OpenAI models at half list price
One API key — No separate provider accounts to manage
Cost tracking — See exactly what each session costs in your dashboard
Response caching — Repeated requests hit cache automatically

Configuration Details

Provider Setting

Always use provider: openai in your Continue config. Halfbill exposes an OpenAI-compatible API, so Continue's OpenAI provider handles all models correctly — including Claude.

Project-Specific Config

Place a .continue/config.yaml in your project root to override the global config for that project:

name: project-config
version: 0.0.1
models:
  - name: gpt-5.5
    provider: openai
    model: gpt-5.5
    apiBase: https://api.halfbill.uk/v1
    apiKey: llmgtwy_your-api-key-here

Using with the --config Flag

Point to any config file:

cn --config path/to/config.yaml

Switching Models

Add multiple models to your config and switch between them in the Continue interface. In the CLI, you can specify a model with the --model flag if supported, or update your config file.

Troubleshooting

"Failed to parse config" error

Make sure your config file includes name and version fields at the top level:

name: halfbill
version: 0.0.1
models:
  - ...

Onboarding wizard still appears

If running cn without --config shows an onboarding prompt, create the sentinel file to skip it:

touch ~/.continue/.onboarding_complete

Or always launch with the --config flag to bypass onboarding entirely.

Need help? Email support@halfbill.uk.