Quickstart

1. Create or copy your API key

Open Dashboard > API Keys and copy your Claudexia key:

sk-aw-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

2. Make your first Anthropic-format request

bash
curl https://api.claudexia.tech/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-aw-YOUR_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4.5",
    "max_tokens": 512,
    "messages": [
      {"role": "user", "content": "Say hello from Claudexia."}
    ]
  }'

3. Or use the OpenAI-compatible format

bash
curl https://api.claudexia.tech/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-aw-YOUR_KEY" \
  -d '{
    "model": "claude-sonnet-4.5",
    "messages": [
      {"role": "user", "content": "Say hello from Claudexia."}
    ]
  }'

4. Cursor setup

In Cursor, choose the OpenAI-compatible connection and use:

  • OpenAI Base URL: https://api.claudexia.tech/v1
  • OpenAI API Key: your Claudexia key from the dashboard

Important: custom API access in Cursor requires a paid Pro plan or higher. Pro trial (7 days) does not work for custom API endpoints; only paid plans do.

5. Claude Code setup

Claude Code should use:

  • ANTHROPIC_BASE_URL=https://api.claudexia.tech
  • ANTHROPIC_API_KEY=sk-aw-YOUR_KEY

Important: for Claude Code the base URL is without /v1.

Linux/macOS:

bash
export ANTHROPIC_BASE_URL="https://api.claudexia.tech"
export ANTHROPIC_API_KEY="sk-aw-YOUR_KEY"
claude

Windows PowerShell:

powershell
$env:ANTHROPIC_BASE_URL = "https://api.claudexia.tech"
$env:ANTHROPIC_API_KEY = "sk-aw-YOUR_KEY"
claude

6. List models

bash
curl https://api.claudexia.tech/v1/models

7. Billing basics

Claudexia uses pay-as-you-go billing:

  • You pay per 1M tokens for each model
  • Current rates are available at https://api.claudexia.tech/v1/models/info

Next steps

  • Go to IDE Integration for the setup overview
  • Open Claude Code, VS Code Extensions, or OpenCode for dedicated setup pages
  • Go to Streaming for SSE examples
  • Go to Pricing for per-model rates