Editors and IDEs

Cursor, Trae, Cline, Roo Code, and Continue can all connect to HopBase. Choose the provider type for the model first, then enter its Base URL, plan key, and model ID.

Choose the provider type by model

Model	Provider type	Base URL	Key
GPT models such as gpt-5.6-sol or gpt-5.6-terra	OpenAI Compatible	`https://api.hop-base.com/v1`	Codex Plus or Codex Pro group key
Gemini models such as gemini-3.8-flash	OpenAI Compatible	`https://api.hop-base.com/v1`	Gemini (all models, incl. image) or Gemini Official Direct group key
GLM models such as glm-5.3	OpenAI Compatible / Chat Completions	`https://api.hop-base.com/v1`	GLM Official Direct group key
Claude models such as claude-sonnet-5	Anthropic	`https://api.hop-base.com` without `/v1`	Claude Max (Official, Full Quota) or Claude Max (Official, Full Quota) - Limited-Time Offer group key; Claude Max (ccmax) works only in Claude Code

Copy all current model IDs and see current pricing in the model catalog after signing in.

Confirm the model and plan key

Call GET /v1/models with the target plan key and copy an ID from the response.

Add a custom provider

Use the table above to set the provider type, Base URL, API key, and model ID.

Send a minimal test

Select the new model and send “Reply only with ok.” Enable tools, images, or long-context features only after the basic request works.

Claude keys cannot use OpenAI Compatible.

A Claude plan key does not support OpenAI Compatible mode. That mode uses an OpenAI protocol path and returns a 404. If the extension has no Anthropic provider type, use Cline, Roo Code, Continue, Trae, or the web console.

Cline and Roo Code

In extension settings, set API Provider to OpenAI Compatible for GPT models or Anthropic for Claude models. Enter the matching Base URL, API key, and model ID.

Continue

# models section in ~/.continue/config.yaml
models:
  - name: HopBase GPT
    provider: openai
    model: gpt-5.6-sol
    apiBase: https://api.hop-base.com/v1
    apiKey: sk-openai-plan-key
  - name: HopBase Claude
    provider: anthropic
    model: claude-sonnet-5
    apiBase: https://api.hop-base.com
    apiKey: sk-claude-plan-key

Cursor

GPT, Gemini, or GLM: In Cursor Settings → Models → API Keys, enter the matching plan key, enable Override OpenAI Base URL, set https://api.hop-base.com/v1, and add the model ID.
Claude: Use the Anthropic API Key field and override the Anthropic Base URL with https://api.hop-base.com in a recent Cursor release.

Built-in features such as Tab completion still use Cursor's service. These settings apply to the custom model selected in Chat.

Trae

Open Settings, Models, then Add model. Select OpenAI Compatible for GPT or Anthropic for Claude. Enter the matching Base URL, API key, and model ID.

Match the key to the provider type.

Keys follow groups: Claude models require a Claude Max group key and the Anthropic provider; GPT models require a Codex Plus / Codex Pro group key and the OpenAI Compatible provider. The same rule applies to Zed, JetBrains AI, and other editors.

Next steps

Third-party clients: configure Cherry Studio, NextChat, or LobeChat
Available models: find the model IDs available to a key
Troubleshooting: look up an error message

On this page