Cursor, Claude Code and other tools

Most AI-enabled editors, agents and chat front-ends let you bring your own provider. Because Claud serves both the OpenAI Chat Completions format and the Anthropic Messages format with standard sk- keys, they work with Claud without plugins or proxies. This page collects the exact settings for the most common tools.

Everything below needs the same three values:

Cursor#

Cursor lets you route its chat and inline-edit requests to any OpenAI-compatible endpoint.

1. Open Cursor Settings → Models.
2. Under OpenAI API Key, paste your Claud sk-... key.
3. Expand the section, enable Override OpenAI Base URL, and enter https://api.claudkey.com/v1.
4. Click Verify. Cursor sends a small test request; it should succeed and the key turns green.
5. Under the model list, click + Add model and enter the Claud slug(s) you want to use, such as claud-5.1, claud-opus and claud-flash. Tick them and untick the built-in models you do not want to see.
6. Select a Claud model from the picker in Chat or Cmd/Ctrl-K.

Requests are sent from Cursor's servers, so the base URL must be publicly reachable; a local proxy will not work. Some Cursor features (for example Tab completions) only run on Cursor's own models regardless of provider settings.

Base URL : https://api.claudkey.com/v1
API key  : sk-...
Models   : claud-5.1, claud-opus, claud-flash

Claude Code#

Claude Code reads its endpoint from environment variables. Set them in your shell profile (or a project .env that your shell loads) and launch as normal:

export ANTHROPIC_BASE_URL="https://api.claudkey.com"
export ANTHROPIC_AUTH_TOKEN="sk-..."          # sent as Authorization: Bearer
export ANTHROPIC_MODEL="claud-opus"        # main model
export ANTHROPIC_SMALL_FAST_MODEL="claud-flash" # background / quick tasks
claude

ANTHROPIC_API_KEY (sent as x-api-key) works too; use one or the other. You can also pin these in ~/.claude/settings.json under "env" so they apply to every session. Inside Claude Code, /model lets you switch between any Claud slug.

Cline and Roo Code#

Both extensions support an OpenAI Compatible provider and an Anthropic provider with a custom base URL.

• Provider: OpenAI Compatible
• Base URL: https://api.claudkey.com/v1
• API key: sk-...
• Model ID: claud-5.1 (or any Claud slug)

Enable Supports images for vision-capable models and leave Supports computer use off.

Continue#

Add Claud to ~/.continue/config.yaml:

models:
  - name: Claud 5.1
    provider: openai
    model: claud-5.1
    apiBase: https://api.claudkey.com/v1
    apiKey: sk-...
    roles: [chat, edit, apply]
  - name: Claud Flash
    provider: openai
    model: claud-flash
    apiBase: https://api.claudkey.com/v1
    apiKey: sk-...
    roles: [autocomplete]

Aider#

export OPENAI_API_BASE=https://api.claudkey.com/v1
export OPENAI_API_KEY=sk-...
aider --model openai/claud-5.1

Zed#

In ~/.config/zed/settings.json:

{
  "language_models": {
    "openai": {
      "api_url": "https://api.claudkey.com/v1",
      "available_models": [
        { "name": "claud-5.1", "display_name": "Claud 5.1", "max_tokens": 128000 }
      ]
    }
  }
}

Then set the OpenAI API key in the assistant panel to your sk-... key.

Open WebUI, LibreChat and other chat front-ends#

Add a new OpenAI API connection:

• URL: https://api.claudkey.com/v1
• Key: sk-...

The front-end will call GET /v1/models and list every Claud model your plan allows. Nothing else needs configuring.

LiteLLM and other proxies#

If you fan out across providers with LiteLLM, add Claud as an OpenAI-compatible backend:

model_list:
  - model_name: claud-5.1
    litellm_params:
      model: openai/claud-5.1
      api_base: https://api.claudkey.com/v1
      api_key: os.environ/CLAUD_API_KEY

Troubleshooting#

Still stuck? Open a ticket from the Support page with the x-request-id header of a failing request and we will trace it.