
None
None
Long Story Video Skill
Turn your idea into 10s–10min video—AI writes scripts, prompts, and generates footage automatically.

Ads Video Skill
Generate professional ads and sales videos—AI auto-generates scripts, prompts, and footage.
3D Science Explainer Video Skill
Convert scientific concepts into stunning 3D explain animations
Feedback
freeTrialImage.bannerPity
freeTrialImage.upgradeUnlock
- ✓freeTrialImage.benefitHd
- ✓freeTrialImage.benefitWatermark
- ✓freeTrialImage.benefitUnlimited
AI Ad Video Example
Loading...
Space Bunny AI Model
Space Bunny AI Model sits on TokenRA as a $0 stealth release that reads text, images and video while keeping its provider unnamed.
All Tools
Discover our comprehensive AI-powered animation toolkit
MiniMax H3
MiniMax H3 AI Video Generator
Seedance 2.5
The Future of AI Video Is Here.

Seedance 2.0
The Future of AI Video Is Here.
FLUX 3 Video Generator

Kling 3.0
Next-Gen AI Video Generator
Grok Video Generator
Create Videos from Text or Images with AI
MiniMax H3 video generator
MiniMax H3 AI Video Generator

Seedance 2.0
The Future of AI Video Is Here.
What Makes Space Bunny AI Model Different
TokenRA lists Space Bunny AI Model under a codename only: the lab stays anonymous, access is free during preview, and every claim below notes where it came from.
- No Vendor Page, Only a CodenameThe entry sits under the slug space-bunny-alpha with no model card, launch post or company name anywhere on TokenRA — the codename is the only identifier you get.
- Multimodal Input Backed by a Million-Token ContextThree details define the entry: video is accepted alongside images, the context window is stated at 1,000,000 tokens with output capped at 524,288, and preview usage costs nothing.
- Where Each Claim Comes FromAnonymous releases invite wild guessing, so everything stated here is tagged as provider-declared, third-party measured or pure hypothesis — and you can see which is which.
Getting Space Bunny AI Model Running
Three steps take you from a blank TokenRA signup to a live space-bunny-alpha call.
What Space Bunny AI Model Can Do
A walk through the space-bunny-alpha entry as written: context size, multimodal input, streaming behaviour and the $0 preview.
A Stated 1,000,000-Token Context
The listing declares 1,000,000 tokens of context and up to 524,288 tokens of output, though no independent test has confirmed either figure so far.
Accepts Video and Images, Not Just Text
Prompts can carry text, stills or clips, and the reply comes back as text. Vision is the thinnest-documented part of the entry, so treat it as a bonus rather than a promise.
A Reasoning-Effort Dial You Control
Push reasoning effort up and the model spends more thinking tokens before replying, trading speed for depth — noticeable against the 80 tok/s P50 logged in the 24 September 2026 snapshot.
Streaming That Reports Errors Mid-Flight
Once a stream is open, a failure cannot come back as an HTTP status, so TokenRA delivers it as a server-sent event with finish_reason: "error"; a handler that only inspects the opening response will cut output off without warning.
Preview Access Priced at $0
No payment method, extra signup or model card is needed — the entry reads $0 — but past stealth previews have closed as soon as a lab claimed the model.
Tokenizer Fingerprints Point to a Family
The clearest clue so far is measurement rather than marketing: probes run by the stealthprint project match the MiniMax tokenizer family, which narrows the suspects without naming one.
Space Bunny AI Model: Questions Answered
Answers on the space-bunny-alpha entry, its declared specs and how long the free window may last.
Does Space Bunny Alpha cost anything?
As of writing the entry reads $0 and no card is required. That said, earlier stealth previews stopped being free the moment the model was claimed and repriced.
Which lab, if any, has claimed Space Bunny Alpha?
Nothing is confirmed. The provider field is blank, the tokenizer is tagged only as "Other" and the knowledge cutoff is empty, so linking it to MiniMax M3.1 remains a guess built on tokenizer-family evidence.
Which input types are supported?
Text, images and video go in; text comes out. That range is the main draw, yet it is also the part of the entry with the least documentation behind it.
How large are the context window and output limit?
The declared figures are 1,000,000 tokens of context and 524,288 tokens of maximum output, and no outside party has verified them so far.
What do I need before I can call the API?
An API key plus any OpenAI-compatible client aimed at the base URL with the right model slug. Keep your balance at or above zero, or even free models will turn you away.
How long do stealth free windows normally stay open?
Every stealth Alpha model followed since early 2026 has been claimed, usually by a Chinese lab and typically within about a week of launch; Ox Alpha lasted roughly six free days. Treat that as history, not a forecast.
Use Space Bunny AI Model Before the Preview Ends
Read the live TokenRA entry alongside the API walkthrough, build for the day the lab is revealed and pricing changes, and keep anything sensitive away from an unidentified provider.
