You're paying to wait.
We fixed that.
You love Claude. You love Codex. But both have brutal limits — you're in the middle of a feature, deep in flow, and suddenly you're locked out for hours. OpenLimits gives you both — Claude from Anthropic + Codex from OpenAI — unlimited, one key, one price.
Real Claude + Real Codex. $200/mo. No cooldowns.
Claude requests go to Anthropic (Opus, Sonnet, Haiku). Codex/GPT requests go to OpenAI (GPT-5, GPT-5.4, Codex). Two providers, one key, zero limits. Cheaper than Claude Max + Codex Pro combined.
Effort Levels
Effort parameter — low, medium, high — works out of the box. Dial quality vs speed per request. Use low for quick edits, high for complex architecture decisions.
Your Own Dashboard
Real-time analytics, live request feed, per-model breakdowns, token tracking. Know exactly where every token goes. See input, output, cache reads, and cache writes per request.
Works With Everything
One API key works everywhere: Conductor, OpenCode, Claude Code CLI, Codex Desktop, OpenClaw, Cursor, direct API, and any OpenAI-compatible client.
No More 4-Hour Cooldowns
Other users report getting locked out for hours after just a few messages. With OpenLimits, you never see a cooldown. Your workflow stays unbroken, no matter how heavy the session.
Built for devs who ship
Not a toy. Real infrastructure with real observability.
Full Streaming
Real-time SSE streaming, fully native. No wrappers, no latency overhead. Tokens appear in your editor the moment Anthropic generates them — identical to calling the API directly.
Token Analytics
Input, output, cache reads, cache writes — per request. See where your tokens go. Daily and weekly trends, cost estimates, and model-level breakdowns all in one dashboard.
Model Breakdown
Usage by model, daily trends, cost estimates. Switch between Opus, Sonnet, and Haiku freely — your dashboard tracks everything automatically with per-model charts and tables.
Live Feed
Watch requests stream in real-time. Filter by model, see tokens flow as they happen. Debug issues instantly by inspecting individual requests — model, tokens, latency, status, all visible.
Zero Downtime
No cooldowns, no waiting, no “please try again later.” Your requests always go through. Automatic failover between provider accounts means if one hits a limit, we seamlessly switch to another.
Native Codex + Claude
GPT-5, GPT-5.4, and Codex models route directly to OpenAI. Claude model aliases translate automatically. One /v1/chat/completions endpoint, both providers — no code changes needed.
Extended Thinking
Full support for extended thinking with budget control. Let Claude reason through complex problems step by step. Works with streaming — see the thinking process in real-time.
PDF & Image Support
Send PDFs, images, and other media in your requests. Full multimodal support, same as the direct Anthropic API. No extra configuration required.
Works with every tool you use
Set one environment variable. Every tool picks it up automatically.
Conductor
Automatically inherits your Claude Code CLI settings. Or set ANTHROPIC_BASE_URL and ANTHROPIC_API_KEY in Settings → Env.
Claude Code CLI
Export two env vars in your shell profile and every Claude Code session routes through OpenLimits. Extended thinking, streaming, tool use — everything works.
OpenCode
Same environment variables. OpenCode picks them up on launch. No config files to edit, no settings to change.
Cursor
Add OpenLimits as an API provider in Cursor's settings. Use Claude models without any subscription limits getting in your way.
OpenClaw
Point OpenClaw to our base URL and use your API key. Full compatibility with all OpenClaw features.
Direct API & SDKs
Anthropic Python/TypeScript SDK, OpenAI SDK, cURL — any client that supports a custom base URL works. See our API docs for examples.
OpenLimits vs Claude Max + Codex Pro
Both providers, unlimited, for less than either alone. Built for developers, not casual users.
| Claude Max ($100-200/mo) | Codex Pro ($200/mo) | OpenLimits ($200/mo) | |
|---|---|---|---|
| Claude models | Yes (with limits) | No | Yes, unlimited |
| Codex/GPT models | No | Yes (with limits) | Yes, unlimited |
| Rate limits | 5x/20x Pro limits | Per-model caps | None |
| Cooldowns | Still hits caps | Still hits caps | Never |
| Effort levels | No | No | Yes |
| Extended thinking | Limited | Limited | Unlimited |
| API access | No | Yes | Full REST API |
| Token analytics | No | No | Full dashboard |
| Works with dev tools | Web only | Codex Desktop | CLI, Cursor, Codex, SDKs, etc. |
| Automatic failover | N/A | N/A | Yes |
| Combined price | $300-400/mo | $200/mo | |
How it's built
Production-grade infrastructure you can rely on.
Edge Deployed
Runs on Cloudflare Workers at the edge, close to you. Typical added latency is under 50ms. Your requests hit our nearest edge node before being proxied to Anthropic.
Legitimate & Secure
We use our own enterprise API accounts purchased directly from Anthropic — no stolen keys, no scraped credentials. All traffic encrypted in transit. We don't log or store your prompts or completions. Your API key is scoped to your account only.
Real-Time Tracking
Every request is tracked with model, token counts, latency, and status. Usage data refreshes every 5 minutes. Live feed updates in real-time via server-sent events.
99.9% Uptime
Edge-deployed with automatic failover and health monitoring. When Anthropic is up, we're up. No single points of failure in the proxy layer.
Stop hitting limits. Start shipping.
Starting at $200/month. Real Claude from Anthropic. No cooldowns. No caps. Every model. Set up in 30 seconds.
Get Your API Key →