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 runs free on TokenRA as the unnamed space-bunny-alpha endpoint — 1M-token memory plus text, image and video prompts.
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 AI Model Preview Actually Offers
TokenRA lists the Space Bunny AI Model as an unnamed preview: no vendor page, no model card, no charge, and each spec below marked with where it came from.
- An Anonymous Codename, Not a Branded ReleaseOn TokenRA the Space Bunny AI Model shows up only as space-bunny-alpha, with the provider field hidden — there is no launch post, model card or company page to cross-check.
- 1M-Token Context With Text, Image and Video InputThree details define the listing: video prompts work alongside images, the window holds 1,000,000 tokens with a 524,288-token output cap, and nothing is charged while the preview lasts.
- Every Spec Here Is Source-TaggedUnnamed models invite confident guesswork, so details about the Space Bunny AI Model are grouped as provider-stated, independently measured or hypothesis-only, each with its origin noted.
Running Space Bunny AI Model: Three Steps
Go from a blank TokenRA account to a live space-bunny-alpha call in three moves.
Space Bunny AI Model: Capabilities and Limits
A breakdown of what the space-bunny-alpha listing claims — context size, multimodal input, streaming behaviour and preview pricing.
Context Window: 1,000,000 Tokens
The listing declares a 1,000,000-token context and a 524,288-token maximum output; so far nobody independent has published a reproduction of either figure.
Image and Video as Input
The Space Bunny AI Model takes text, images and video in and gives text back — vision is the thinnest-documented surface here, so treat it as a bonus rather than a settled guarantee.
Reasoning Effort You Can Dial
Reasoning effort trades latency for quality: a higher setting spends more thinking tokens before the answer, which shows against the 80 tok/s P50 recorded in the 24 September 2026 snapshot.
Streaming With Errors Delivered as Events
Once streaming starts, a failure can no longer travel as an HTTP status, so TokenRA emits it as a server-sent event with finish_reason: "error" — code that only checks the first response will truncate output silently.
Preview Pricing at $0
The listing prices the preview at $0 with no extra signup, model card or card on file, and past stealth previews have ended the moment the model was claimed.
Tokenizer Fingerprints Point to a Family
The clearest public identity clue is a measurement rather than a statement: stealthprint tokenizer probes land inside the MiniMax family, narrowing the search without naming the lab.
Space Bunny AI Model: Questions Answered
Answers to the questions people ask most about this anonymous listing, its specs and how long free access may last.
Does using Space Bunny Alpha cost anything?
Nothing at the moment — the listing shows $0 for the preview and asks for no payment method. That said, earlier stealth previews were retired and repriced once the model was claimed.
Which company is behind Space Bunny Alpha?
Unconfirmed. The provider field is hidden, the tokenizer is labelled only "Other" and the knowledge cutoff sits empty, so the MiniMax M3.1 link remains a hypothesis built on tokenizer-family evidence rather than a vendor statement.
Which input types can I send?
Text, images and video all go in, and text comes back — that multimodal reach is a big part of the draw, though it is also the least documented part of the listing.
How large is the context window and output cap?
The provider declares a 1,000,000-token context window and a 524,288-token maximum output; neither figure has been reproduced by a third party yet.
What setup does the API require?
A TokenRA API key plus an OpenAI-compatible client pointed at the base URL with the model slug is all it takes — and a negative account balance blocks even free models until you top up.
How long do stealth free windows typically stay open?
Every stealth Alpha model tracked since early 2026 has eventually been claimed, most of them by Chinese labs, usually around a week after appearing; Ox Alpha held on for roughly six days. That pattern is history, not a forecast for this listing.
Test the Space Bunny AI Model Before the Free Window Closes
Open the live TokenRA listing and the step-by-step API walkthrough, build for the day this model gets claimed and repriced rather than reacting to it, and never send data you would not hand to an unknown operator.