VS Code extension · ScaleMax integration
Set up Cline with the ScaleMax API
Cline connects through its OpenAI Compatible provider. Paste the ScaleMax base URL and the raw key, pick a model ID, and leave the custom headers empty.
- Choose in the client
- API provider: OpenAI Compatible
- Protocol
- OpenAI Chat Completions
- ScaleMax installer
- Supported
- Video lesson
- In the dashboard
Cline settings for ScaleMax
Enter these values in Cline. A Pay as you go key and a token pack key use different base URLs — use the one that matches the key you bought.
| Setting | Value |
|---|---|
| API provider | OpenAI Compatible |
| Base URL | https://api.scalemax.pro/v1 (Pay as you go key) or https://api.scalemax.pro/token/v1 (token pack key) |
| API key | The raw sm_live_… key — no “Bearer ” prefix |
| Model ID | One exact ID from scalemax models or GET /v1/models |
| Custom headers | Leave empty |
Step by step
- Open Cline’s settings and select the OpenAI Compatible provider.
- Paste the ScaleMax base URL that matches your key.
- Paste only the raw key. Do not add “Bearer ” or a custom Authorization header.
- Choose an exact model ID, save, and reload the VS Code window.
- Use Act mode when you want Cline to edit files — Plan mode is read-only.
Or let the installer do it
Close VS Code completely first, then choose Cline. The installer only writes Cline versions it has been checked against; it tells you if yours is newer.
npm install -g scalemax@latest && scalemax updateA recorded walkthrough is on the Video setup page in the ScaleMax dashboard (sign-in required).
Models to use in Cline
Rates are the published ScaleMax rates per million tokens, read from the live catalogue. Your key must include a model before Cline can call it — GET /v1/models with the key lists exactly which.
Claude models
| Model | Model ID | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
| Claude Haiku 4.5 | claude-haiku-4-5-20251001 | $1 | $5 |
| Claude Haiku 5.5 | claude-haiku-5-5 | $0.20 | $1 |
| Claude Opus 4.6 | claude-opus-4-6 | $5 | $25 |
GPT models
| Model | Model ID | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
| GPT-6.1 Sol | gpt-6.1-sol | $2 | $10 |
| GPT-6 Sol | gpt-6-sol | $2 | $10 |
| GPT-6 Luna | gpt-6-luna | $0.10 | $0.50 |
DeepSeek, Gemini and other models
| Model | Model ID | Input / 1M tokens | Output / 1M tokens |
|---|---|---|---|
| DeepSeek V4 Pro | deepseek-v4-pro | $1 | $4 |
| DeepSeek V4 Flash | deepseek-v4-flash | $0.19 | $0.51 |
| Gemini 3.8 Flash | gemini-3.8-flash | $0.75 | $3.75 |
Good to know
- Cline CLI is configured differently from the VS Code extension: it uses the Responses API, so its key needs a Responses-capable model with tool support.
- If Cline asks for a context window, use the value the catalogue publishes for that model.
Troubleshooting
- Models load, but every request fails with an authentication or load error
- Remove any “Bearer ” prefix from the key field and delete custom Authorization or x-api-key headers. Cline adds the header itself.
- Cline only describes changes and never edits files
- Switch from Plan mode to Act mode.
- Settings did not take effect
- Save, then run “Developer: Reload Window” in VS Code.
ScaleMax is not affiliated with the makers of Cline. Compatibility describes the API protocol; Cline's own features and plans are provided by its developer.
Cline and ScaleMax: questions
Which Cline provider should I choose for ScaleMax?
OpenAI Compatible. Paste the ScaleMax base URL, the raw key and an exact model ID. This works for Claude, GPT and the other models your key includes.
Is there a video for setting up Cline?
Yes. The Video setup page in the ScaleMax dashboard has a Cline VS Code lesson for Windows and macOS. You need to be signed in to watch it.
Why does Cline say authentication failed when the model list loaded?
Usually because the key was pasted with a “Bearer ” prefix or a custom auth header was added. Paste the raw key only and leave custom headers empty.
Related setup guides
Run Cline on a prepaid key
Pay by UPI, card or crypto, copy the base URL and model ID, and you are coding in minutes. No subscription.