Setup guides
Setup guides for every tool that speaks the OpenAI protocol
Every guide below starts from a working install of the tool and ends with a request that actually reaches QuickRouter. One API key works across all of them, so you only create a key once.
Start here
Claude CodePoint ANTHROPIC_BASE_URL at the gateway host and pin the Claude model you want to pay for.CursorSet the OpenAI base URL override, then add the model names Cursor is allowed to call.CodexUse OPENAI_BASE_URL or a model provider block in config.toml, and keep the key in an env var.opencodeRegister the gateway as an OpenAI-compatible provider in opencode.json and pick models per agent.Cherry StudioAdd a custom OpenAI-compatible provider to the desktop client, then list the models you want.TraeConfigure a custom model provider and confirm the session is not falling back to a built-in model.
Model prices and background reading
Every guide ends with a model, so the price pages below give you the per-token rate before you paste a model name into a config file.
What is an LLM API gateway?The definition behind every guide on this page, and when a gateway layer is worth adding.GPT-5$1.25 per 1M input and $10.00 per 1M output, 400K context.GPT-5 mini$0.25 per 1M input and $2.00 per 1M output, 400K context.Claude Sonnet 4.5$3.00 per 1M input and $15.00 per 1M output, 200K context.Claude Opus 4.1$15.00 per 1M input and $75.00 per 1M output, 200K context.Claude Haiku 4.5$1.00 per 1M input and $5.00 per 1M output, 200K context.Gemini 2.5 Pro$1.25 per 1M input and $10.00 per 1M output, 1M context.Gemini 2.5 Flash$0.30 per 1M input and $2.50 per 1M output, 1M context.DeepSeek V3.2$0.28 per 1M input and $0.42 per 1M output, 128K context.Grok 4$3.00 per 1M input and $15.00 per 1M output, 256K context.
One key covers every model in this guide
Create an account, pick a plan and copy an API key. Gateway plans start at $19 per month and model usage is billed at upstream list prices.