import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "stealth/space-bunny-alpha", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "stealth/space-bunny-alpha", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"stealth/space-bunny-alpha","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
Free while cloaked — pricing after the stealth window is unknown.
| Benchmark | Score | What it measures | Source | Retrieved |
|---|
Coding, agentic workflows and multimodal work, per the stealth slot's own description. Reasoning is always on, with the effort level adjustable per request.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Space Bunny Alpha This page | Coding and long-context agentic work | |||
| Agentic coding and long-context research | ||||
| Coding + agents | ||||
| Deep reasoning + long-context agents | ||||
| Coding + agents |
Space Bunny Alpha is an anonymous large model served from the OpenRouter stealth slot: fast inference, strong coding, native image input and always-on reasoning over a 1,000,000-token context. No vendor has claimed authorship — that is what “stealth” means.
It is free on AI/ML API while it is cloaked. What it will cost once the stealth window closes has not been announced.
Unknown. Stealth models are published without an author so a lab can gather feedback before announcing the model under its real name. Any attribution circulating right now is speculation.
1,000,000 tokens in, up to 524,288 tokens out — enough for whole repositories and long reports in one call.
Send a POST request to https://api.aimlapi.com/v1/chat/completions with stealth/space-bunny-alpha as the model id and your AI/ML API key in the Authorization header. The endpoint is OpenAI-compatible, so an existing SDK only needs the base URL swapped.
