VS Code extension · ScaleMax integration
Set up Roo Code with the ScaleMax API
Roo Code uses its OpenAI Compatible provider. Set the base URL, an exact model ID, streaming on, and the context and output limits the catalogue publishes for that model.
- Choose in the client
- API provider: OpenAI Compatible
- Protocol
- OpenAI Chat Completions
- ScaleMax installer
- Supported
- Video lesson
- In the dashboard
Roo Code settings for ScaleMax
Enter these values in Roo Code. 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) |
| Model ID | One exact ID from the catalogue |
| Streaming | On |
| Context window / max output | The model’s published context_window and max_output_tokens |
Step by step
- Open Settings → API Provider and choose OpenAI Compatible.
- Enter the base URL for your key and the exact model ID.
- Turn streaming on. Copy the context window and maximum output from the model’s catalogue entry.
- Switch “Include max output tokens” on only after entering a positive maximum.
- Work in Code or Debug mode — Ask and Architect modes cannot run terminal commands.
Or let the installer do it
Choose Roo Code. The installer writes import profiles into VS Code and the VS Code forks where Roo is installed. Run scalemax update again after changing keys.
npm install -g scalemax@latest && scalemaxA recorded walkthrough is on the Video setup page in the ScaleMax dashboard (sign-in required).
Models to use in Roo Code
Rates are the published ScaleMax rates per million tokens, read from the live catalogue. Your key must include a model before Roo Code 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
- Never choose the “OpenAI Codex” provider or its sign-in for a ScaleMax key; it expects an OpenAI account.
- Never leave an enabled token limit blank or set it to -1. Roo sends that value as max_completion_tokens.
- DeepSeek models work in Roo when the catalogue reports tool support for them.
Troubleshooting
- Stuck at “API Request…” with “Could not find ripgrep binary”
- Run npx scalemax@latest fix-roo, then “Developer: Reload Window”. This is a Roo and VS Code packaging issue, not a ScaleMax one.
- Requests are rejected for their token limit
- Set max output to a positive number no larger than the model’s published max_output_tokens, or switch “Include max output tokens” off.
- Roo signs in to OpenAI instead of using your key
- You picked the OpenAI Codex provider. Switch to OpenAI Compatible.
ScaleMax is not affiliated with the makers of Roo Code. Compatibility describes the API protocol; Roo Code's own features and plans are provided by its developer.
Roo Code and ScaleMax: questions
Which Roo Code provider works with ScaleMax?
OpenAI Compatible, with the ScaleMax base URL, your key and an exact model ID. Do not use the OpenAI Codex provider.
What context window should I enter in Roo Code?
The context_window and max_output_tokens the ScaleMax catalogue publishes for the model you chose. Each model page on scalemax.pro lists both.
Can the ScaleMax installer set up Roo Code?
Yes. Install the CLI with npm install -g scalemax@latest, run scalemax and choose Roo Code. It writes a ready import profile.
Related setup guides
Run Roo Code 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.