Space Bunny Alpha is live — 1M context, pay per token

Space Bunny Alpha —
1M context, multimodal, fast.

A stealth model gaining traction across coding agents — a 1,000,000-token context window, multimodal input, and strong coding performance, served fast. Drop it into your app via our API, or run it in your terminal via opencode.

▶ Try it nowGet API access →Use in opencode
1M token context$3 per 1M tokensMultimodal + reasoning
Model minimax/minimax-m3Price $3/M totalReleased Sep 23, 2026 LiveChecked Oct 14
Live · streamed from the real API
promptWrite a haiku about a bunny coding among the stars.
Space Bunny is thinking…
Open full playground →
POST spacebunnymodel.com/api/v1/chat/completions
system prompt (optional)
your message129c
real API · streamed · prepaid key
Space Bunny's answer streams in here.
Pick a preset, edit the prompt, and hit Run Space Bunny.
Why Space Bunny

What makes it worth trying

A model with frontier-scale context, served fast — now named and paid, at $3 per 1M tokens.

1,000,000-token context

Drop a whole repo, a long transcript, or a book into a single call. 1M tokens in, up to 524k out — no chunking gymnastics.

Simple pay-per-token

Space Bunny Alpha is prepaid — $3 per 1M total tokens. Top up from $5 and point your code at our hosted endpoint.

Reasoning + multimodal

Adjustable reasoning effort, native text-vision-audio-video input, strong coding, and blazing-fast inference.

The 1M advantage

A context window that holds the whole thing

Most models cap out long before a real codebase or document fits. Space Bunny Alpha takes 1,000,000 tokens in a single call — and returns up to 524,288.

Typical model128K
Extended context200K
Space Bunny Alpha1M
≈ 750,000 wordsa whole repo in one callhours of transcriptsfull docs + code
Three ways to use it

Pick your path to Space Bunny

Use it in opencode, a drop-in hosted API, or a 1M-context tool inside your agent — your call.

opencode

Use it in opencode

Point opencode at our OpenAI-compatible endpoint and code with a 1M-context model in your terminal.

opencode setup →
API

Our hosted API

One OpenAI-compatible key, managed metering and a usage dashboard. Prepaid from $5, then pay as you go at $3 per 1M tokens. Drop it into any SDK, CLI or agent.

Get an API key →
MCP

Add it to your agent

Give Claude Code, Cursor or opencode a 1M-context tool via MCP — offload whole-repo analysis to Space Bunny.

Install the tool →
1M
Input context window
524k
Max output tokens
$3/M
Per 1M tokens
4
Input modalities
FAQ

Space Bunny, answered

What is Space Bunny Alpha?

Space Bunny Alpha is a large language model with a 1M-token context window, native multimodal input, adjustable reasoning, and strong coding, served fast. Build on it through our hosted, OpenAI-compatible API.

Who made Space Bunny?

MiniMax. It launched as an anonymous 'stealth' preview that community reverse-engineering pegged as MiniMax M3; that stealth listing has since ended and the model is now served under MiniMax's named id minimax/minimax-m3 on OpenRouter.

What does Space Bunny cost?

The hosted API is prepaid: top up from $5 and pay per token at $3 per 1M total tokens (prompt + completion) for a stable, metered, OpenAI-compatible endpoint. Grab a key at /get-api-key.

How do I use Space Bunny in opencode?

Point opencode's OpenAI-compatible provider at our endpoint (or OpenRouter) and select space-bunny-alpha. Full step-by-step on our opencode integration page.

How big is the context window?

1,000,000 input tokens and up to 524,288 output tokens — one of the largest available, ideal for whole-codebase and long-document tasks.

Try Space Bunny Alpha now

Prepaid from $5, pay per token, streamed from the real API. Grab a key to use it anywhere.

Open the playground ▶
Space Bunny Alpha — free 1M-context LLM playground & API