Space Bunny Alpha API

space-bunny-alpha is an anonymous (“stealth”) model: its maker has not been disclosed, and BeatAPI does not know or claim who it is. It offers fast inference, strong coding, native multimodal input and adjustable reasoning effort over a 1M-token context window. It sits in BeatAPI’s Free category.

Free for now, not for good. Space Bunny Alpha costs $0 while its free (stealth) period lasts. The period can end, or the model can be withdrawn, at any time and without notice, so do not build anything that cannot fall back to another model. During the stealth period the anonymous provider may log and retain prompts and completions (it states they are not used for training); do not send secrets, credentials or personal data you would not share with a third party.


Model ID	`space-bunny-alpha`
Price	Free: $0 input and$ 0 output per 1M tokens
Context window	1,000,000 tokens
Maximum output	524,288 tokens
Input	Text, image and video
Output	Text
Reasoning	Always on. `reasoning_effort` accepts `low`, `medium`, `high`, `xhigh` or `max`; the default is `max`
Also supports	Tools (function calling), `response_format` for structured output, `temperature`, `top_p`

Free-model limits

Free models have their own per-account limit, separate from the account’s normal request-rate tier:

Before the first top-up: 1 successful request per minute.
After any top-up: at most 10 requests per minute, however much was paid.

Free calls are counted on their own, so they do not use up the paid allowance. A request over the limit gets HTTP 429 with a Retry-After header; wait that long before retrying. Capacity for this free model is also limited on its own, so a request within your limit can still get 503 processing_unavailable; retry it after a short wait.

OpenAI Chat Completions

POST https://api.beatapi.io/v1/chat/completions

import OpenAI from "openai";
const client = new OpenAI({
  apiKey: process.env.BEATAPI_API_KEY,
  baseURL: "https://api.beatapi.io/v1"
});
const completion = await client.chat.completions.create({
  model: "space-bunny-alpha",
  max_tokens: 4000,
  messages: [
    { role: "user", content: "Review this function for off-by-one errors and suggest a fix." }
  ]
});
console.log(completion.choices[0].message.content);

curl --request POST \
  --url https://api.beatapi.io/v1/chat/completions \
  --header 'Authorization: Bearer <BEATAPI_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "space-bunny-alpha",
  "messages": [
    {
      "role": "user",
      "content": "Review this function for off-by-one errors and suggest a fix."
    }
  ]
}'

Because reasoning is always on, the default max effort spends the most tokens and time before answering. Lower reasoning_effort when latency matters more than depth.

Other SDK formats

The same model answers on /v1/responses, /v1/messages and the Gemini-compatible endpoint. The request and response shapes are identical for every text model, so they are documented once on the Text API page rather than repeated here.

Authentication and availability

One BeatAPI key reaches this model, with no separate signup. Send Authorization: Bearer <BEATAPI_API_KEY> against https://api.beatapi.io.

Use GET /v1/models to check that the model is still enabled for your account before relying on it. Once the free period ends or the model is withdrawn, requests naming it stop succeeding, so keep a fallback model configured.