Update, October 19, 2026: MiniMax has named it. At 09:21 UTC MiniMax’s official account posted “Welcome back. Space Bunny.” and “MiniMax-M3.1-Flash is coming.” with a 25-second film of a carrot-shaped rocket stencilled Space Bunny that ends on a MiniMax M3.1 flash title card. The tokenizer fingerprint was right. The model is announced, not released: at 10:05 UTC there were no M3.1 weights on Hugging Face, no M3.1 id or price on OpenRouter, and the stealth listing showed no live endpoints. The record below was written before the reveal; the grades, tracker and timelines are updated.
OpenRouter put a new anonymous model in its catalog at 14:48 UTC on September 23, 2026 and called it Space Bunny Alpha. It is free, it takes text, images and video, it holds a million tokens of context, and nobody has claimed it. Four days later it is one of the most talked-about coding models on X, and the only named company whose product matches it is MiniMax.
This page is the record: what OpenRouter published, what the fingerprinting found, how Space Bunny lines up with the M3.1-Flash-Preview model MiniMax put in its coding app on September 27, and what nobody has confirmed. A disclosure first: we build CellCog, an AI employee platform, and we do not route to Space Bunny Alpha or any stealth endpoint.
On this page · 10 sectionsOpen
OpenRouter listed Space Bunny Alpha as stealth/space-bunny-alpha at 14:48 UTC on September 23, 2026: a 1,000,000-token context, up to 524,288 output tokens, text, image and video input, reasoning that cannot be switched off, and a price of $0 in and out.
MiniMax claimed it on October 19, 2026, 25.8 days after the listing: its official account posted that Space Bunny is MiniMax-M3.1-Flash, which it says is coming. During the preview OpenRouter only routed requests for an anonymous provider.
Three independent tokenizer tests posted on launch day point to MiniMax: one account called it M3.1 outright, one matched 36 of 36 comparisons to the MiniMax M3 tokenizer but stopped at the family, and one matched 50 of 50 strings.
On September 27 MiniMax posted that M3.1-Flash-Preview debuts on MiniMax Code. Its config lists the same three traits as Space Bunny: a 1,000,000-token context, thinking forced on, and effort levels from low to max.
It is fast in OpenRouter’s own numbers: 79 tokens a second and 1.61 seconds latency at the median, 98.96 percent availability over three days. No vendor benchmark exists, because there is no named vendor.
The free window has a clock. OpenCode announced it as free for a week on September 23. Every earlier OpenRouter stealth model lost its free price the moment its maker was named, and Union Alpha lasted 33 hours.
§ 01What OpenRouter published
The listing describes it as “an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support.” On who is behind it, the page is explicit: “It is developed and operated by a third-party provider who has chosen to remain anonymous during this preview.” OpenRouter’s launch post called it “A flash model with fast inference, adjustable reasoning, and a 1M-token context window.” Everything below comes from OpenRouter’s public model API and listing page, read at 14:01 UTC on September 27.
| Item | Value |
|---|---|
| Model id | stealth/space-bunny-alpha |
| Listed | September 23, 2026, 14:48:04 UTC (catalog created timestamp) |
| Maker | Anonymous third-party provider |
| Context and output | 1,000,000 tokens in, up to 524,288 out |
| Input | Text, image and video; text out |
| Reasoning | Mandatory; efforts low, medium, high, xhigh and max, default max |
| Tools | Tool calling (auto only) and structured output |
| Price | $0 input, $0 output |
| Speed, week median | 79 tokens a second, 1.61 seconds latency |
| Tool call error rate | 3.16 percent |
| Availability, three days | 98.96 percent |
§ 02The MiniMax clues, graded
The identity work started within 15 minutes of the launch post. At 15:03 UTC, the account cheaty wrote: “New stealth model ‘Space Bunny’ is most certainly MiniMax M3.1.” Its test compared token counts: “I can independently confirm that the text tokenizer perfectly matches that of the MiniMax M3.” Twenty-six minutes later it added: “Vision tokenizer is a perfect match too, this is most certainly MiniMax-M3.1!”
The more careful read came from MarMar Labs at 16:32 UTC: “My current bet on Space Bunny Alpha is MiniMax. M3.1 is a plausible candidate, but I can’t call the exact model yet.” It made 36 input-token comparisons across 12 text fixtures and every one matched MiniMax’s public M3 tokenizer, with a catch it named itself: “M2.7 matched too, so this points to the family rather than a specific release.” The Qwen, GLM, DeepSeek and Llama tokenizers it tried did not match. YFarmX reached the same family at 17:52 UTC: “We counted how its tokenizer splits 50 test strings. All 50 match MiniMax exactly.”
On September 26 the benchmark account LuminaBench went further, posting that a MiniMax deployment it calls M3-a returns the name space-bunny in its benchmark runs, and predicted: “This comes out of stealth testing Wednesday, i’d expect it to drop the same day”. We cannot check that deployment from outside.
| Claim | Source | Grade |
|---|---|---|
| Made by MiniMax | Three tokenizer tests, September 23 | Confirmed by MiniMax, October 19 |
| Specifically M3.1 | cheaty; MarMar Labs calls it plausible | Confirmed: MiniMax-M3.1-Flash |
| A MiniMax deployment returns space-bunny | LuminaBench, September 26 | Single source, cannot check |
| Leaves stealth on Wednesday, September 30 | LuminaBench | Missed; named October 19 |
| Free for a week | OpenCode, September 23 | Ran past the week; no live endpoints on October 19 |
| Not trained on your prompts | OpenRouter listing and post | Stands; retention still allowed |
§ 03Space Bunny next to M3.1-Flash-Preview
At 05:24 UTC on September 27, MiniMax’s agent account posted: “MiniMax’s latest text model, M3.1-Flash-Preview, debuts today on MiniMax Code.” It added: “Built for everyday development, it’s fast, reliable, and ready for real work, from quick bug fixes to full features.” MiniMax Code’s public model config lists the model, and its three published traits line up with the OpenRouter listing one for one. The older M3, in the same config, does not.
| Trait | Space Bunny Alpha (OpenRouter) | M3.1-Flash-Preview (MiniMax Code config) | MiniMax M3 (same config) |
|---|---|---|---|
| Context | 1,000,000 tokens | 1,000,000 tokens | 450,000 tokens |
| Reasoning | Mandatory | Forced on | Switchable, on by default |
| Effort levels | Low, medium, high, xhigh, max | Low, medium, high, xhigh, max, plus default | Not listed |
| API price | $0 during the preview | Not published | $0.30 in, $1.20 out per million tokens on OpenRouter |
A match on three traits is a strong hint, not a name. At 17:06 UTC on September 27 MiniMax’s official account added: “MiniMax-M3.1 Flash Preview is now live on the Token Plan!” So the model now reaches developers through MiniMax’s paid subscription as well as its coding app. MiniMax’s model release notes still end at July 31, its Hugging Face organization has nothing newer than August 7, and OpenRouter carries no M3.1 id. MiniMax has published no benchmark and no per-token price for it.
§ 04How the week went
Update, September 28, 2026, 19:00 UTC. Usage has caught up with the buzz. On OpenRouter’s public rankings, read at 18:57 UTC, Space Bunny Alpha is the most-used model by tokens on the most recent complete day, 3.99 trillion, ahead of DeepSeek V4.1 Flash at 3.44 trillion. Over the week it sits third with 13.9 trillion tokens, behind DeepSeek V4.1 Flash and GLM 5.3 Flash. OpenCode posted at 16:05 UTC that “space bunny has been the top model on opencode for 5 days straight”, citing 40 trillion tokens. Still no maker named and no price; OpenRouter lists it at $0.
Demand ran ahead of any explanation. OpenCode’s post announcing the free week had passed 990,000 views by September 27, and the posts under the model’s name are mostly builders showing apps made from a screenshot or a sketch.
§ 05The stealth playbook, and its record
OpenRouter has named every earlier stealth model, and the free price ended each time.
| Model | Appeared | Revealed as | Days anonymous |
|---|---|---|---|
| Quasar Alpha | April 3, 2025 | An early GPT-4.1 test | 11 |
| Horizon Alpha | July 30, 2025 | An early GPT-5 checkpoint | 8 |
| Pony Alpha | February 6, 2026 | Z.ai GLM-5 | 5 |
| Ox Alpha | August 20, 2026 | Z.ai GLM-5.3-Flash | 6 |
| Union Alpha | September 16, 2026 | Pareto, by Unbiased | 1.4 |
| Space Bunny Alpha | September 23, 2026 | MiniMax M3.1-Flash | 25.8 |
The last two runs are the useful comparison. Ox Alpha was fingerprinted as GLM from its tokenizer and the fingerprint was right on every count when Z.ai named it six days in. Union Alpha fooled the fingerprinters, because it was a blended model from a startup nobody had guessed. Space Bunny looks like the Ox Alpha case: a clean tokenizer match to one lab’s family, and now a same-spec product from that lab. It was: MiniMax named it on October 19, and Space Bunny now holds the longest anonymous run on this list.
§ 06The data question
OpenRouter’s launch notes say: “This time, the provider does not train on your prompts or completions”. The listing is narrower: “Prompts and completions may be retained by the provider but are not used for training”, with everything else under OpenRouter’s Stealth Model Terms. No training is a real promise; it is not a promise of deletion, and the company holding the data is not named. OpenCode describes its own route as keeping no data, which is a claim about its route, not about the OpenRouter endpoint. For code or documents you would not hand to an unknown company, wait for the name.
§ 07What we are watching for
- The release. MiniMax says M3.1-Flash is coming: weights, a per-token price and an OpenRouter or Hugging Face id would make it real.
- Numbers. A MiniMax model card for M3.1-Flash-Preview, or an independent coding run on the stealth endpoint.
- The stealth-week prompts. What the named maker says about prompts retained during the anonymous window.
§ 08The tracker
| Question | Status |
|---|---|
| Who made it | MiniMax, confirmed October 19 |
| Which model | MiniMax-M3.1-Flash, announced as coming |
| Is it free | Was $0 on OpenRouter; no live endpoints on October 19 |
| Benchmarks | None from MiniMax yet; OpenRouter speed and error rates only |
| Data terms | Retained, not used for training, per the listing |
| Reveal | October 19, 2026, 09:21 UTC |
§ 09Update log
- October 19, 2026, 10:10 UTC. MiniMax named Space Bunny Alpha as MiniMax-M3.1-Flash at 09:21 UTC (official post, time checked against its id), 25.8 days after the listing. Announced as coming; no weights, price or OpenRouter id yet, and the stealth listing showed no live endpoints at 10:05 UTC. Grades, tracker and timelines updated.
- September 28, 2026, 19:00 UTC. Space Bunny Alpha ranks first on OpenRouter by tokens for the most recent complete day (3.99T) and third for the week (13.9T); OpenCode says it has been its top model five days running. No reveal, still $0.
- September 28, 2026, 01:05 UTC. MiniMax’s official account put M3.1-Flash-Preview on its Token Plan subscription (post at 17:06 UTC on September 27, time checked against its id). No per-token price or OpenRouter id yet; the reveal is still open.
- September 27, 2026, 14:10 UTC. Page opened, four days after the listing and nine hours after MiniMax’s M3.1-Flash-Preview post. Listing facts from OpenRouter’s API and page; posts read on X with times checked against their ids; MiniMax Code config read from its public endpoint.
§ 10Sources
- OpenRouter: Space Bunny Alpha listing
- OpenRouter launch post, September 23
- cheaty, tokenizer match, September 23
- MarMar Labs, 36 comparisons, September 23
- MiniMax Agent: M3.1-Flash-Preview on MiniMax Code, September 27
- MiniMax: M3.1-Flash-Preview on the Token Plan, September 27
- MiniMax Code model config
- OpenRouter model rankings, read September 28, 2026, 18:57 UTC
- OpenCode on X, September 28
- MiniMax: Space Bunny is M3.1-Flash, October 19
- Ryan Lee on X, October 19
Q1Is Space Bunny Alpha the same as MiniMax M3.1-Flash-Preview?
Close. MiniMax named Space Bunny as MiniMax-M3.1-Flash on October 19. The preview it put on MiniMax Code on September 27 was called M3.1-Flash-Preview and shared the same three published specs; MiniMax has not said whether the two are the same checkpoint. M3.1-Flash has no weights, API price or benchmarks published yet.
Q2How do people identify a stealth model?
By tokenizer fingerprinting: they send test strings and compare the input-token counts the endpoint reports with the public tokenizers of known model families. A match rules families in or out, but models in one family often share a tokenizer, so it rarely names the exact release. That is why one tester called it MiniMax M3.1 and another stopped at the MiniMax family.
Q3What happens to prompts I send to Space Bunny Alpha?
OpenRouter’s listing says prompts and completions may be retained by the anonymous provider but are not used for training, with everything else under OpenRouter’s Stealth Model Terms. OpenCode described its own route as zero data retention. Treat anything you send as readable by a company you cannot name yet.
Q4Is Space Bunny Alpha good?
Early users praise it for fast coding and multimodal input, and OpenRouter measures 79 tokens a second at the median with a 3.16 percent tool call error rate. There is no vendor benchmark and no independent run we can verify, so quality claims are anecdotes until a named release publishes numbers.
Q5When was Space Bunny Alpha revealed?
On October 19, 2026 at 09:21 UTC, when MiniMax’s official account named it MiniMax-M3.1-Flash: 25.8 days after the listing, the longest anonymous run of any OpenRouter stealth model we track. A benchmark account had predicted September 30.