Cloudidr LLM Ops — Save 75

How does LLM cost tracking work?

Add a tracking header to your existing API calls. Cloudidr proxies requests, logs token usage and cost, and returns the unchanged response. Your API key passes through directly — never stored.

Do you store my API keys?

No. Your API key is passed directly to the provider via HTTPS and discarded immediately. We only track token counts, model names, and costs — never your keys or content.

Do you see my prompts or responses?

No. We only log metadata: model name, token counts, timestamps, and costs. Your prompt and response content never touches our database.

Does this add latency?

Minimal — typically 10–50ms overhead for logging. Intelligent routing decisions are made in-flight with negligible additional delay.

Can I stop using Cloudidr anytime?

Yes. Remove the base_url and tracking header from your code and your app works exactly the same pointing directly at your LLM provider. No lock-in.

What providers do you support?

OpenAI (GPT models), Anthropic (Claude), Google Gemini, and AWS Bedrock — 108 models across all major providers.

How much does Cloudidr cost?

Free starter plan available. Paid plans charge 20% of verified savings — only after you see them. First charge when accumulated savings exceed $5.

How can I verify you don't store my API key?

Test with a limited API key, make requests, then revoke it. Try another request — it will fail immediately, proving we don't cache keys.