Getting started
Overagent documentation
Overagent is a prepaid inference gateway. One key reaches every model in the catalog through three request formats you already have clients for: OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages. There is no subscription and no per-seat pricing — you hold a balance, and each request settles against it at the published rate.
Base URLs
Which base URL you use depends on the client, not on the model. Any model in the catalog can be reached from any of the three formats.
https://api.overagent.cc/v1Anthropic-compatiblehttps://api.overagent.ccThe difference is a historical quirk of the two SDKs: OpenAI clients expect the /v1 to be part of the base URL, while Anthropic clients append /v1/messages to the origin themselves. Putting /v1 in an Anthropic base URL is the single most common setup mistake, and it produces a 404 on a path ending /v1/v1/messages.
Your first request
curl https://api.overagent.cc/v1/chat/completions \
-H "Authorization: Bearer $OVERAGENT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-sonnet-5",
"messages": [{"role": "user", "content": "Hello"}]
}'