GUIDES
Model keys
EERRAA does not resell tokens. You bring your own model key, and every call is billed by your provider, not by us.
Add a provider key
Go to Settings, Model keys, pick a provider, and paste your key. You can add more than one. The key is encrypted before it is stored and is only decrypted to make a call. EERRAA supports three providers today.
| Field | Type | Description |
|---|---|---|
Anthropic | claude | Default model claude-haiku-4-5-20251001. |
OpenAI | gpt | Default model gpt-4o-mini. |
Google | gemini | Default model gemini-2.5-flash. |
The defaults are fast and cheap on purpose, a good fit for a support or in-product agent. You can point a project at a different model from the same provider whenever you want more capability.
Priority and health
Add more than one key and EERRAA tries them in priority order. Each key is health-checked, so a key that is out of quota, revoked, or rate-limited is skipped and the next one is used. That gives you a simple failover: put your primary provider first, a backup second, and chat keeps working through a provider hiccup.
Why bring your own key
The tokens a conversation burns are billed to your provider account, at your negotiated rate, on your existing invoice. EERRAA never sits in the middle of that. There is no per-token markup and no surprise usage bill from us. You own the model relationship, the rate, and the data boundary.
It also means you choose the model. Want Claude for reasoning and GPT as a fallback, or Gemini for cost? That is a settings change, not a migration.
When there is no working key
A project needs at least one healthy key to answer. If every key is missing, invalid, or failing its health check, chat is rejected rather than silently degraded, and the error tells you exactly why:
{
"type": "error",
"content": "PROJECT_NO_API_KEY"
}The fix is always the same: add a working key, or reorder so a healthy one is first. As soon as one passes its health check, chat resumes.