Quickstart

The goal here is one working request, then your first tool wired up. The gateway lives at openllm.sh; swap in sk-llm-YOUR_KEY with your own key as you go.

1. Sign in

Go to openllm.sh and continue with Google. That is your account. There is nothing to install yet.

2. Connect a provider

Go to Providers and connect at least one. You have two ways to do it:

• Paste an API key for Anthropic, OpenAI, Gemini, Kimi, Alibaba DashScope, Z.AI, MiniMax, or AWS Bedrock.
• Connect an account over OAuth for ChatGPT, Gemini CLI, or Kimi Code.

Whatever you connect is stored only as ciphertext. See Security for how that works.

3. Create your OpenLLM key

Go to Keys and create one. It looks like sk-llm-…. Copy it. This single key is what every tool will use.

4. Make your first request

curl https://openllm.sh/v1/chat/completions \
  -H "Authorization: Bearer sk-llm-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "plus",
    "messages": [{"role": "user", "content": "Say hello from OpenLLM."}]
  }'

lite, plus, and ultra are tier aliases. OpenLLM resolves each to a real provider and model through your fallback chain, so you can reorder providers without touching your code. See Concepts and Fallback chains.

Anthropic-style clients can call /v1/messages instead. Embeddings, images, and audio live behind /v1/embeddings, /v1/images/generations, and /v1/audio/*.

5. Wire up a coding tool

Each tool has a one-line installer that bakes in your gateway URL and key. Here is Claude Code:

curl -fsSL "https://openllm.sh/api/setup/claude-code/install.sh" \
  | OPENLLM_API_KEY="sk-llm-YOUR_KEY" bash

That merges into ~/.claude/settings.json without clobbering your existing hooks or permissions, points ANTHROPIC_BASE_URL at your gateway, and maps Opus, Sonnet, and Haiku to the ultra, plus, and lite tiers. Restart Claude Code and it routes through OpenLLM.

Full instructions for every tool, including Codex, the Kimi CLI, and Raycast, are on Connect your tools.

You are done

Anything that speaks OpenAI or Anthropic now runs on your accounts through one key. Good next steps:

• Set up Fallback chains so a task never stalls when one provider is down.
• Read Why it is compliant to understand what OpenLLM does and does not do with your accounts.