Cursor + OpenCompress

Name: OpenCompress
Author: OpenCompress

One line change. Zero registration. Keep your own API key and save 40-60% on every request.
Works with OpenAI, Anthropic, Google, and OpenRouter keys.

Open Cursor Settings

Go to Settings > Models > OpenAI API Key. Paste your API key — OpenAI (sk-proj-...), Anthropic (sk-ant-...), Google (AIza...), or OpenRouter (sk-or-...) all work. We auto-detect your provider from the key prefix.

Note: Anthropic / Google keys go in the OpenAI API Key field — not their own fields. We translate the API format automatically. To use multiple providers at once, use an OpenRouter key which gives you access to all models through a single key.

Override Base URL

Check "Override OpenAI Base URL" and paste the URL below. This routes all requests through OpenCompress for automatic compression.

https://www.opencompress.ai/api/v1

Done — Start Coding

That's it. All requests are now compressed automatically. Same models, same experience, 40-60% lower token cost. Free tier: 5 req/min.

Note: Check response headers for X-OpenCompress-Tokens-Saved to see compression in action.

Verify (Optional)

Test from the terminal to confirm compression is working:

curl https://www.opencompress.ai/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o-mini","messages":[{"role":"user","content":"Hello"}]}'

Upgrade for Dashboard + Higher Limits

Free tier has no stats and 5 req/min. Sign up for a usage dashboard, 120 req/min, and $10 free credit.

Go to Dashboard →

Other Tools

Same approach works with any tool that lets you set a base URL.

# Continue.dev — config.json
{
  "models": [{
    "provider": "openai",
    "model": "gpt-4o",
    "apiBase": "https://www.opencompress.ai/api/v1",
    "apiKey": "YOUR_KEY"
  }]
}

# Aider
aider --openai-api-base https://www.opencompress.ai/api/v1

# Cline — Settings
API URL: https://www.opencompress.ai/api/v1

# Any OpenAI SDK
client = OpenAI(
    base_url="https://www.opencompress.ai/api/v1",
    api_key="YOUR_KEY",
)

FAQ

Common questions about the transparent proxy.

Do you store my API key?

No. Your key is forwarded directly to the upstream provider in memory and never persisted.

What's the rate limit?

Free tier: 5 req/min. Registered: 120 req/min + usage dashboard + $10 free credit.

Which providers are supported?

OpenAI (sk-proj-*), Anthropic (sk-ant-*), OpenRouter (sk-or-*), and Google (AIza*) keys are auto-detected.

How do I use Claude in Cursor?

Put your sk-ant-* key in the OpenAI API Key field (not Anthropic). We auto-translate between OpenAI and Anthropic API formats.

Can I use multiple providers?

Cursor's Override Base URL only applies to one key at a time. To access GPT, Claude, Gemini, and more from a single key, use an OpenRouter key (openrouter.ai) — it supports all major models through one API.

Start Saving

Every LLM call gets cheaper. One line change, zero code modifications.

Go to Dashboard Read the Docs