VS Code extension · ScaleMax integration

Set up Continue with the ScaleMax API

Continue reads models from ~/.continue/config.yaml. Add a model block with provider openai, the ScaleMax apiBase and a key from your secrets file, and it is ready for chat and edit.

Get an API key Full Continue guide

Updated October 14, 2026

Choose in the client: provider: openai with a custom apiBase in config.yaml
Protocol: OpenAI Chat Completions
ScaleMax installer: Supported
Video lesson: Not yet

Continue settings for ScaleMax

Enter these values in Continue. 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
Config file	~/.continue/config.yaml
Key	SCALEMAX_API_KEY=… in ~/.continue/.env
apiBase	https://api.scalemax.pro/v1 (or https://api.scalemax.pro/token/v1 for a token pack)
useResponsesApi	false

~/.continue/config.yaml

models:
  - name: ScaleMax
    provider: openai
    model: claude-haiku-4-5-20251001
    apiBase: https://api.scalemax.pro/v1
    apiKey: ${{ secrets.SCALEMAX_API_KEY }}
    useResponsesApi: false
    roles:
      - chat
      - edit

Step by step

Put SCALEMAX_API_KEY=your-key in ~/.continue/.env.
Add the model block to ~/.continue/config.yaml with the apiBase for your key.
Set model to an exact ID your key includes and keep useResponsesApi: false.
Reload VS Code and pick the ScaleMax model in Continue’s model menu.

Or let the installer do it

The installer adds the Continue model block and installs the Continue extension if VS Code is present.

Terminal

scalemax login && scalemax update && scalemax doctor

Models to use in Continue

Rates are the published ScaleMax rates per million tokens, read from the live catalogue. Your key must include a model before Continue can call it — GET /v1/models with the key lists exactly which.

Claude models

Claude models for Continue
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

DeepSeek, Gemini and other models

DeepSeek, Gemini and other models for Continue
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

GPT models

GPT models for Continue
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

Good to know

Keep the key in .env, never in a workspace config that could be committed.
Tool calling is available only for models whose catalogue entry reports tool support.

Troubleshooting

Requests go to /responses and fail: Set useResponsesApi: false on the model block.
Continue cannot find the key: Check the variable name in ~/.continue/.env matches ${{ secrets.SCALEMAX_API_KEY }} exactly.

ScaleMax is not affiliated with the makers of Continue. Compatibility describes the API protocol; Continue's own features and plans are provided by its developer.

Continue and ScaleMax: questions

Which provider should Continue use for ScaleMax?

provider: openai with apiBase set to the ScaleMax base URL. ScaleMax serves its chat models, Claude included, over the OpenAI Chat Completions protocol.

Why must useResponsesApi be false in Continue?

The ScaleMax setup for Continue uses Chat Completions. Leaving the Responses API on sends requests to a different endpoint shape than this configuration expects.

Can the ScaleMax CLI configure Continue?

Yes. Run scalemax login, scalemax update and scalemax doctor. It writes the model block and checks the connection with a small billable request.

Related setup guides

Run Continue 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.

Get an API key All integrations