STEP-BY-STEP / UPDATED OCTOBER 3, 2026
How to Use Space Bunny Alpha
You can try Space Bunny Alpha from the chat page on this site. The anonymous provider is not publicly identified, and free access is a time-limited preview. This workspace requires a free account to send messages; there is no payment-card step. Follow the steps below to reach the model and understand what each limit means.
Note: Chat here requires a free sign-in. The anonymous model's free preview is time-limited.
Step 1: Open the chat and sign in
Select “Start chat” on this page. If you are signed out, the site will ask you to sign in before it sends a request. Continue with Google, or create an email account and verify the message sent to your inbox. If the email signup allowance is full for the day, Google sign-in remains the alternative. You can read public guides without an account, but sending chat messages is authenticated.
A heading that promises “no login” would be inaccurate for this site. Sign-in keeps conversations attached to your account and helps enforce a fair daily allowance across the shared preview. No card, top-up, or paid subscription is part of this first release.
Step 2: Start with a focused text question
Type a question into the composer and send it. A concrete task is easier to judge than a broad request: include the code fragment, error text, or decision criteria relevant to your question. The reply is generated by the Space Bunny Alpha model through OpenRouter, not by a model built by this site. Keep important facts and generated code under review before you rely on them.
This preview allows up to 20,000 characters per message, keeps 20 recent context messages, and uses an 8,192-token output budget including reasoning. Those are workspace limits, not claims about the model's full context window. A multi-turn conversation can carry a follow-up question, but earlier details may leave the retained context as the conversation grows.
Step 3: Add an image or a short video if needed
Attach up to three images or one MP4 video, with no more than 2.5 MB combined upload. Ask what you want extracted or compared. The published model supports text, image, and video input with text output. A video request may still fail if the upstream account or provider rejects it; this site cannot guarantee every clip, URL, or codec will work.
For a first test, upload a small image and ask it to describe one visible detail. Then ask a follow-up about the same image in that conversation. For video, use a short MP4 rather than WebM: our earlier local acceptance check succeeded with MP4 and failed with WebM. Do not upload confidential or personal material to an anonymous preview.
Step 4: Choose controls only when they help
The composer offers adjustable reasoning effort, a JSON output option, and bounded tools for arithmetic, unit conversion, and current time. Choose a higher reasoning effort for difficult reasoning tasks, but expect it to spend more of the output budget. JSON output helps with structured notes; do not assume a strict schema will always be enforced. The site's tools do not provide open web search or arbitrary code execution.
One successful reply counts against the daily allowance. The default preview allowance is 50 successful replies per account per UTC day, resetting at 00:00 UTC. A failed request is designed to release its reserved count, although an interruption can delay the displayed usage. The free window depends on the anonymous upstream provider; OpenRouter showed an October 5, 2026 removal notice when checked October 3.
What to do when something fails
If you see a sign-in error, return to the login page and begin a fresh Google or email flow rather than reusing an old callback URL. If you are out of daily replies, wait for the next UTC reset. If an attachment fails, reduce its size and confirm the video is MP4. If a provider response fails or an upstream balance rule blocks video, a retry may work later, but repeated rapid retries are unlikely to fix an account-level restriction.
This is a short-lived, anonymous preview, so availability can change without notice. The provider's identity is not public, and the free period is not a permanent offer. Check the live model listing if the chat stops responding after the advertised window.
Frequently asked questions
Can I chat without logging in?
No. Public guide pages are open, but this site's chat requires Google sign-in or a verified email account. No payment card is needed.
How many free replies can I send?
The default is 50 successful replies per account per UTC day. The allowance resets at 00:00 UTC and can change if the preview configuration changes.
Why did my video upload fail?
Use a small MP4 within the 2.5 MB combined upload cap. Upstream video processing or account rules can still reject a request.
Can the model create images or spoken audio here?
No. This workspace uses image and video as inputs and displays text replies. It does not publish image, video, or speech generation.
What if Google login sends me back to the homepage?
Start a fresh sign-in from the login page. If the problem persists, use verified email login and contact support with the error text, without sharing a password or token.
Why does JSON not match my exact schema?
The model listing supports a JSON response format but does not promise JSON Schema enforcement. Validate the result in your own workflow.
Sources and updates
Model information was checked on October 3, 2026. Upstream availability can change without notice; this site's allowance and upload limits come from its current implementation.
Anonymous provider. Time-limited free access. Sign-in and daily allowance apply.