Questions you probably have
Everything you need to know about OpenLimits. If your question isn't here, check our API docs.
Is there a catch?
No hidden fees. Plans are recurring subscriptions that renew automatically until you cancel — cancel anytime from the billing portal. Full refund within 14 days if you haven't used the service at all. After any usage, all sales are final. See our Refund Policy.
Is this built for agents?
Yes. OpenLimits is positioned for OpenClaw, Hermes, Pi, Conductor, OpenCode, Cursor, Claude Code CLI, Codex Desktop, and custom workers that need stable API-compatible model access.
What models do I get?
Plans are grouped by access: Core includes unlimited GLM, MiniMax, and DeepSeek; Agents adds unlimited Claude Sonnet/Haiku and Codex mini; Max adds unlimited Claude Opus and Codex/GPT model groups.
Can this get me banned?
No. You're not using anyone else's account or violating any terms. We use our own enterprise accounts purchased directly from Anthropic and OpenAI. Your usage goes through our infrastructure — your personal accounts are never involved or at risk.
Does it work with Claude Code CLI?
Yep. Set one environment variable and it works exactly as you'd expect — extended thinking, streaming, tool use, everything. Most users are set up in under 30 seconds.
What about rate limits?
No 5-hour rolling limits, no 7-day caps, no getting locked out after 3 prompts. There is a global rate limit of 30 requests per second — if you exceed it, you'll get a short ~10 second cooldown. Normal usage (even heavy coding sessions) stays well under that.
Is setup actually 30 seconds?
Yes. Get a key, paste one env variable, done. We timed it. Multiple times. It's 30 seconds. See How It Works for step-by-step instructions.
Can I track my usage?
Your own dashboard with real-time analytics, request history, model breakdowns, token tracking (input, output, cache reads, cache writes), and a live feed. It's pretty nice.
What tools are supported?
Conductor, OpenCode, Claude Code CLI, Codex Desktop, OpenClaw, Hermes, Pi, Cursor, compatible APIs directly, and both the Python and TypeScript SDKs.
Does it work with Codex Desktop?
Yes. Codex Desktop can use the Codex/GPT model group on plans that include it. Same API key and dashboard. See our API Docs for details.
Billing questions
How does billing work?
All plans are recurring subscriptions. Core, Agents, Max, Week, and Day renew on their configured intervals until you cancel. Manage or cancel anytime from the billing portal in your dashboard.
What happens when I cancel?
Your subscription stops renewing and your access continues until the end of the period you've already paid for. No data loss — your dashboard and analytics history remain. You can resubscribe anytime.
Can I cancel anytime?
Yes. Manage or cancel your subscription anytime from the Stripe billing portal in your dashboard. Access continues until the end of the period you've paid for, then stops renewing. Full refund within 14 days if you haven't used the service.
Why is it so cheap compared to the API?
We pool resources efficiently across users. You get API-level access at a fraction of the per-token cost. The math works because not everyone is coding 24/7.
Technical questions
Is my data private?
Yes. We don't store your prompts or responses — they pass through and are never logged. Only metadata (model, token counts, timestamps) is tracked for your analytics dashboard. All API access uses our own enterprise accounts purchased directly from Anthropic and OpenAI — no stolen keys, no scraped credentials, no gray-market access.
What's the latency overhead?
Minimal. We're edge-deployed on Cloudflare Workers. Typical added latency is under 50ms. For streaming responses, you won't notice any difference — tokens arrive as fast as Anthropic generates them.
Can I use it for production apps?
Yes. Same Anthropic API, same models, same reliability. We add automatic failover on top — if a provider account hits a temporary error, we seamlessly switch to another. 99.9% uptime.
Do you support tool/function calling?
Yes. Full tool_use support, exactly the same as the direct Anthropic API. Define tools in your request and Claude will call them as needed. Works with streaming too.
Do you support PDFs and images?
Yes. Full multimodal support — send PDFs, images, and other media in your messages. Same as the direct Anthropic API, no extra configuration.
What if Anthropic or OpenAI is down?
If a provider's API is down, requests to that provider are down too — we're a proxy, not a replacement. But our automatic failover handles most transient errors (429s, 529s) by switching provider accounts. Claude and Codex are independent, so if one goes down the other still works.
Still have questions?
Try it with a Day Pass — full access, every model, no limits. Cancel anytime before it renews. See our plans.
Get Your API Key →