
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 as space-bunny-alpha on TokenRA: no-cost preview, 1M-token context, and text, image plus video input. Check the specs first.
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.
Space Bunny AI Model: A Codename-Only Release Explained
Space Bunny AI Model shows up on TokenRA as space-bunny-alpha: no named provider, no model card, no charge while the preview lasts, and a source label attached to every statement below.
- A Codename Release With No Named ProviderOn TokenRA the Space Bunny AI Model is filed under space-bunny-alpha, and the codename is the only identifier available — there is no vendor page, model card or launch announcement to cross-check against.
- Multimodal Input Paired With a 1M-Token WindowThree details define this listing: video joins image as an accepted input type, the context window reaches 1,000,000 tokens with output capped at 524,288, and preview usage currently costs nothing.
- Every Claim Here Carries a Source TagCodenames invite confident guesswork, so statements about the Space Bunny AI Model are sorted into provider-stated, independently measured and hypothesis-only, with the origin marked on each one.
Getting Space Bunny AI Model Running in Three Steps
Go from a blank TokenRA account to a live space-bunny-alpha call without any guesswork along the way.
Space Bunny AI Model: Documented Capabilities and Open Gaps
What the space-bunny-alpha listing genuinely states, from its context window and multimodal input through to streaming error handling and zero-cost preview pricing.
A 1,000,000-Token Context Window
TokenRA lists a context window of 1,000,000 tokens and a maximum output of 524,288 tokens — figures that, so far, no outside tester has independently reproduced.
Video, Image and Text Input
The endpoint takes text, images and video in and returns text, yet vision remains the thinnest-documented surface of the listing, so treat it as a bonus rather than a settled capability.
Reasoning Effort You Can Tune
Reasoning effort is the main quality-versus-latency dial: pushing it higher spends more thinking tokens before the answer appears, which shows up clearly against the 80 tok/s P50 recorded in the 24 September 2026 snapshot.
Streaming Plus Event-Level Error Handling
Once streaming has begun, a failure cannot travel back as an HTTP status code, so TokenRA emits it as a server-sent event carrying finish_reason: "error" — a handler that checks only the opening status will quietly truncate output.
Zero-Cost Preview Pricing
The listing prices preview access at $0 with no separate signup, model card or payment method required, and free stealth previews have historically closed once a model was claimed.
Tokenizer Fingerprints From Third Parties
The clearest public identity signal is a measurement rather than an announcement: tokenizer probes run by the stealthprint project point toward the MiniMax tokenizer family, narrowing the field without naming the lab.
Space Bunny AI Model Questions, Answered
Straight answers about the space-bunny-alpha stealth listing, its published specs and how long the free window may stay open.
Is Space Bunny Alpha free to use?
Yes — at the time of writing the listing prices preview access at $0 and asks for no payment method, although free stealth previews have historically ended once a model was claimed and repriced.
Has any company claimed Space Bunny Alpha?
Not confirmed. The provider stays hidden, the tokenizer is tagged only as "Other" and the knowledge cutoff sits empty, so the MiniMax M3.1 link remains a hypothesis resting on tokenizer-family evidence rather than a vendor statement.
What input types does the model accept?
Text, images and video all go in, and text comes back — that range is why many users reach for it, though the multimodal surface is the least documented part of the listing.
What is the context window and maximum output length?
The provider states a 1,000,000-token context window alongside a 524,288-token maximum output; no third party has reproduced those numbers yet.
What do I need before calling the API?
A TokenRA API key and an OpenAI-compatible client aimed at the base URL with the model slug will do — and a negative account balance blocks access even to free models until credits are added.
How long does a stealth free window usually last?
Every stealth Alpha model tracked since early 2026 has been claimed, most of them by Chinese labs, generally about a week after appearing; Ox Alpha stayed free for roughly six days. That base rate is not a forecast for this model.
Run Space Bunny AI Model Before the Free Window Closes
Open the live TokenRA listing together with the step-by-step API guide, plan for the reveal-and-reprice switch now instead of on the day it lands, and never send data you would not hand to an unidentified third party.
