Use AI Badgr with Continue

Drop-in OpenAI replacement for Continue

1

Set API Key

Set your API key in your environment:

Set your API key
export OPENAI_API_KEY=your_api_key_here

Note: Continue reads OPENAI_API_KEY. You can safely put your AI Badgr key here. Get your API key from aibadgr.com/signup

2

Test with curl

Test your API key before configuring Continue:

Test API connection
curl -s https://aibadgr.com/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 10
  }'

Expected: You should see a JSON response. Look for: choices[0].message.content. If you get an error, check the troubleshooting section below.

3

Set Base URL

In your Continue config.json (~/.continue/config.json), add or update the model configuration:

config.json
{
  "models": [{
    "title": "AI Badgr (Cheap OpenAI-compatible)",
    "provider": "openai",
    "model": "gpt-4o-mini",
    "apiBase": "https://aibadgr.com/api/v1"
  }]
}

Important: Your apiBase must be the OpenAI-style root that contains /chat/completions under it. Use: https://aibadgr.com/api/v1

4

(Optional) Change Model

You can switch models without changing anything else:

Recommended: gpt-4o-mini (cheap) or gpt-4o (better).

Other OpenAI-compatible names may work, but start with these.

5

Try in Continue

Open Continue and try: "Summarize this file"

You should see a response.

✓ That's it! You're now using AI Badgr with Continue.

Supports streaming + JSON mode.

AI Badgr is OpenAI-compatible. No refactor. You can switch back anytime.

If it doesn't work

404 Not Found

Your apiBase is wrong. It must be the OpenAI-style root that contains /chat/completions under it. Use: https://aibadgr.com/api/v1

401 Unauthorized

Your API key isn't set or wrong. Check that you exported OPENAI_API_KEY in the same shell where Continue is running. Restart Continue after setting the key.

Model not found

If you see "model not found", start with gpt-4o-mini or gpt-4o.

Config file issues

Make sure your ~/.continue/config.json has valid JSON syntax. Check for trailing commas or missing quotes. Restart Continue after editing the config.

Most Continue users run everyday tasks on AI Badgr and keep OpenAI/Claude for edge cases.