The bars are off.
Chimaera 1 is our own uncensored LLM, and the one that answers every request. The prices below come straight from the table that bills you.
One model.Ours.
The same id answers in chat and over the API. It streams, calls tools, returns JSON and reads the live web when you ask it to.
Chimaera1
Our own model. No refusals, no lecture.
Chimaera 1 is the model we built in-house, and the only one we serve. It answers the question you asked instead of the one it was comfortable with: reasoning, code, long-form writing, tool calls and live web search, through the OpenAI-compatible API and in chat.
What it does.Five switches, one id.
Every one of these is a field on the same request. Nothing to install, no second model to route to.
OpenAI chat completions, streamed token by token or returned whole.
"stream": trueChat completions Hand it functions. It calls them OpenAI style, then reads your results back.
"tools": [ … ]Tools Ask for JSON and the reply is JSON, ready for a parser.
"response_format": { "type": "json_object" }Chat completions It can think before it answers. The thinking may stream ahead of the reply.
delta.reasoning_contentStreaming It searches the web first and cites what it read.
"model": "…:online"Web search venym/chimaera-1:online
One suffix on the model id, or "venym": { "web_search": true } in the body. A search runs first and the answer cites its sources.
POST /v1/chat/completions
{
"model": "venym/chimaera-1:online",
"messages": [
{
"role": "user",
"content": "What is the latest stable release of Example Framework?"
}
]
}Old ids still answer.Swap them when you can.
The launch models were retired on 1 Nov 2026. Requests that still name them are answered by Chimaera 1 and billed at its price, so nothing breaks while you move.
The response always names the model that answered: "model": "venym/chimaera-1".