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
Meet Space Bunny AI Model — TokenRA's free space-bunny-alpha preview with a 1M-token window and text, image and video input.
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 the space-bunny-alpha Listing Actually Tells You
Nobody has claimed this codename yet. Space Bunny AI Model sits on TokenRA with the provider masked, no charge during preview, and every spec on this page tagged with where it came from.
- A Codename With No Vendor Behind ItOn TokenRA the entry is listed simply as space-bunny-alpha. There is no company page, no model card and no launch post — the codename is the only thing identifying it.
- Multimodal Input Plus a Million-Token WindowThree details separate it from a typical preview: video joins images as accepted input, the context window reaches 1,000,000 tokens with output capped at 524,288, and nothing is charged while the preview runs.
- Where Each Spec on This Page Comes FromAnonymous releases invite guesswork, so every statement about Space Bunny AI Model is sorted into provider-stated, independently measured, or hypothesis-only, and the tag travels with it.
Getting space-bunny-alpha Running in Three Moves
Start with nothing but a TokenRA signup and finish with a live request to the space-bunny-alpha endpoint.
Space Bunny AI Model Specs, Read Line by Line
Every number and behaviour the entry declares — window size, accepted input types, streaming failure handling and the $0 preview price.
A Context Window of 1,000,000 Tokens
The entry declares a 1,000,000-token window and 524,288 tokens of maximum output. Nobody outside the provider has published a replication of either number.
Image and Video as Accepted Input
Text, stills and clips all go in; only text comes back. Visual handling is the thinnest-documented area of the entry, so treat it as a bonus rather than a guarantee.
A Reasoning-Effort Dial You Control
Turn effort up and the model spends more thinking tokens before answering, trading latency for quality; the 24 September 2026 snapshot recorded 80 tok/s at P50.
Errors Arrive as Events Mid-Stream
Once streaming begins, a failure can no longer be reported through an HTTP status, so TokenRA emits a server-sent event carrying finish_reason: "error". Code that only inspects the opening status will quietly cut output short.
Priced at $0 During the Preview
The entry reads $0 while in preview, with no extra signup, card or payment method required. Past stealth previews stopped being free the moment a lab claimed the model.
A Tokenizer Fingerprint, Measured Not Announced
The clearest public clue comes from measurement rather than marketing: tokenizer probes run by the stealthprint project match the MiniMax tokenizer family, narrowing the suspects without naming a lab.
Space Bunny AI Model: Questions People Keep Asking
Straight answers on the space-bunny-alpha entry, its declared specs and how long the free window may last.
Does Space Bunny Alpha cost anything?
No. At the time of writing the entry reads $0 and asks for no card. That said, stealth previews have always ended the moment a lab claimed the model and set a price.
Has a lab come forward to claim it?
Nothing is confirmed. The provider field is masked, the tokenizer is tagged only as "Other" and the knowledge cutoff sits empty — which keeps the MiniMax M3.1 link a tokenizer-based guess, not an announcement.
Which input types can I send?
Text, images and video go in, text comes out. That range is what draws most visitors, yet it is also the part of the entry with the fewest documented details.
How large is the context window and the output cap?
The entry claims a 1,000,000-token window and up to 524,288 tokens of output. No independent test has reproduced those figures so far.
What do I need before making a call?
A TokenRA key plus any OpenAI-compatible client set to the base URL and model slug. Keep the balance positive: a negative total cuts off access even to models listed at $0.
How long do stealth free windows normally stay open?
Since early 2026 every stealth Alpha tracked has been claimed, most by Chinese labs, usually within about a week of launch; Ox Alpha held out roughly six days. That history is a base rate, not a forecast for this one.
Use Space Bunny AI Model Before the Price Appears
Open the TokenRA entry and the walkthrough guide, plan for the switch from free to paid before it happens rather than after, and never send data you would not hand to an unnamed third party.