SteadyRouterDocs

Docs › Setup guides

Use SteadyRouter with n8n

n8n's OpenAI and Anthropic credentials both have a Base URL field. Point them at SteadyRouter, and the OpenAI and Anthropic nodes (including the AI Agent's chat model sub-nodes) work as usual. Use the Anthropic credential for Claude models, so Claude features such as prompt caching and extended thinking work the way they do with Anthropic's API.

Before you start

  1. Create a SteadyRouter account.
  2. In the console, open API Keys and copy your key. New accounts come with one called Default Key, on Lowest price (see below). To make another, click Create API Key. Keep Smart routing on: if a group fails, the request is retried in the next group within the same call. A new key starts on Auto, or on Lowest price if your balance is under US$1.
  3. Find the model names you want on Model Square, for example gpt-5-mini.

OpenAI credential (most models)

  1. In n8n, create a new credential of the type OpenAI.
  2. API Key: your SteadyRouter key.
  3. Leave Organization ID (optional) empty.
  4. Base URL:
    URL
    https://api.steadyrouter.com/v1
  5. Save. n8n tests the credential by listing the models.

Use it in the OpenAI Chat Model node (for example under an AI Agent) and pick a model by name, for example gpt-5-mini. The node's Use Responses API option is on by default; turn it off for models that aren't from OpenAI, so the node uses Chat Completions, which works with every chat model on SteadyRouter. The OpenAI node always uses the Responses API, so use it with OpenAI models only.

Anthropic credential (Claude models)

  1. Create a new credential of the type Anthropic.
  2. API Key: your SteadyRouter key.
  3. Base URL:
    URL
    https://api.steadyrouter.com
  4. Save.

Use it in the Anthropic Chat Model node or the Anthropic node, with a model such as claude-sonnet-5-5.

Trying it on a small balance

New accounts currently start with US$0.05 of credit. Before each request, the gateway reserves balance based on the input plus the maximum output the request asks for. To make a small balance last:

  1. Use Lowest price under Smart routing on your API key. Default Key is already on it; for another key, choose it when you create the key or later by editing it.
  2. Start with a smaller model, and keep Maximum Number of Tokens in the model node's options at 8192 or less. On Lowest price, a request to claude-haiku-5-5 or gpt-5-mini costs a small fraction of the same request to larger models such as claude-sonnet-5-5, gpt-5.5 or claude-opus-5-5.

Once you've confirmed everything works, add funds, and switch the key back to Auto if you prefer.

Lowest price often puts Pool groups first: usually cheaper, sometimes less stable. In every smart routing mode, Pool and Mixed groups can be used, so for stability-critical work, turn smart routing off and list only cloud or API groups on the key. See Models and groups.

If something goes wrong

What you seeWhat to do
The credential test fails with 404Check the Base URL: https://api.steadyrouter.com/v1 for OpenAI, https://api.steadyrouter.com for Anthropic.
401 Invalid tokenThe key is wrong, disabled, expired or out of its spending cap. Check it under API Keys.
403 insufficient_user_quotaYour balance can't cover the request. Top up, or follow the small-balance steps above.
503 model_not_foundThe model name is wrong, or the groups your key uses don't offer it. Check the name on Model Square.
429Over 300 requests per minute for your account, or the upstream is rate-limiting. Turn on Retry On Fail in the node's settings and set Wait Between Tries (ms).
408, 504 or 524An upstream timeout. These are not moved to another group automatically, so retry.

Every error message ends with a request id. Include it when you email support@steadyrouter.com.

More: API docs · Model Square