LLM API is a developer-focused API relay — one key, Claude as the flagship, routing the Anthropic, OpenAI and Gemini protocols through a multi-provider pool. Unlimited tokens, full tool support, set up in two environment variables.
# one command, fully configured
PS> irm llmapi.pro/setup.ps1 | iex# or two env vars, manually
$ export ANTHROPIC_BASE_URL=https://api.llmapi.pro:99
$ export ANTHROPIC_API_KEY=your-key
$ claude
Works with all Claude Code terminals and IDE plugins
01 — Models
Full compatibility with the latest Claude model family
The ideal balance of intelligence, speed, and cost. Default model for Claude Code — fast enough for real-time coding.
claude-sonnet-4-6
World-class coding, complex reasoning, and advanced multi-step analysis. The strongest model for agentic tasks.
claude-opus-4-8
Ultra-fast responses for simple tasks, quick edits, and Q&A. Native image understanding built-in.
claude-haiku-4-5
02 — The Problem
Average developer spends $6/day on Claude API tokens. That adds up fast.
Rate limits kill your flow. You hit the cap right when you need it most.
LiteLLM breaks, proxies fail, tool calling doesn't work. Hours wasted debugging.
We solved all three.
03 — How It Works
Three steps. No configuration files. No proxy servers.
Get your API key in 30 seconds. Free tier included.
Add these to your shell and you're done.
Claude Code works exactly the same. No changes needed.
# Point Claude Code to LLM API
$ export ANTHROPIC_BASE_URL=https://api.llmapi.pro:99
$ export ANTHROPIC_API_KEY=your-key
# That's it. Start coding.
$ claude
04 — Included
Built for Claude Code from the ground up.
Every endpoint Claude Code uses. Messages, streaming, tool calling, extended thinking. Complete compatibility.
Control your Claude Code from phone — scan QR, chat syncs, seamless cross-device. Not available on official Claude.
Track tokens, monitor costs, manage API keys. All in one place.
Multi-provider failover. If one backend goes down, we switch automatically. Your work never stops.
05 — Why Us
Official API charges per token — one feature can cost tens of yuan. Our fixed monthly fee, unlimited tokens, one price no matter how much you use. Plans start at ¥59/mo, while the equivalent official experience runs into the hundreds. Making AI coding affordable.
Multi-node load balancing, automatic failover, smart 429 retry. Your Claude Code won't be interrupted by backend fluctuations. 24/7 uptime to support your development rhythm.
No VPN, no credit card, no overseas phone number. Two env vars and you're ready. Alipay payment in CNY. Solving the biggest barrier for Chinese developers using Claude Code.
06 — Pricing
Unlimited tokens. Pick a plan and code.
07 — Voices
Switched from the official API and saved $150 in the first month. Setup took literally two minutes. Everything just works.
Marcus T.
Full-stack Developer
I was burning through my Pro plan in under an hour. Now I code all day without worrying about limits. The tool support is flawless.
Sarah K.
Backend Engineer
Our team of 4 moved to the Team plan. We went from $800/month combined to $99. The failover means we've had zero downtime.
James R.
Engineering Lead
08 — FAQ