Space Bunny Alpha API: 1M-Context Anonymous Model

A 1M-context anonymous model

Space Bunny Alpha is a multimodal model available on TokenRa as space-bunny-alpha. It accepts text, image and video input, returns text, and provides a 1,000,000-token context window with up to 524,288 tokens of output. It launched as an anonymous stealth release; on October 19, 2026 MiniMax confirmed that Space Bunny was an early version of MiniMax M3.1 Flash. See the MiniMax M3.1 Flash API (released version) for current specs and pricing.

Space Bunny Alpha specifications

The values below reflect the specifications published for this model. Confirm the live limits and availability for your account in the TokenRa console before relying on them.

• Model ID: space-bunny-alpha; developed by MiniMax (confirmed on October 19, 2026 as an early version of MiniMax M3.1 Flash) and operated independently of TokenRa.
• Released September 23, 2026; priced at $0.09 input and $0.36 output per 1M tokens on TokenRa.
• Context window 1,000,000 tokens; maximum output 524,288 tokens.
• Input and output: text, image and video in, text out.
• Tool calling supported through tools and tool_choice; structured output through response_format, with JSON schema accepted but not strictly enforced.
• Reasoning effort is adjustable on the enabled integration.
• Data handling: prompts and completions are retained by the provider and are not used for training.

Where Space Bunny Alpha fits

Its combination of 1M context, video input and a low per-token price shapes where it works well — and where it does not.

• Repository-scale code reading and analysis inside a single context window.
• Long-document summarisation and research where chunking would lose the thread.
• Video and screen-capture review: interface walkthroughs, recorded demos, tutorial material.
• Agentic workflows with tool calls, clear stopping conditions, and application-level validation.
• Prototyping and evaluation where low per-token cost matters more than a service guarantee.

How to get a Space Bunny Alpha API key

Register for TokenRa, open the dashboard, create an API key, confirm that Space Bunny Alpha is enabled for your account, and then send an OpenAI-compatible request from your server. Keep the key private and verify the live model identifier before production use.

curl https://tokenra.io/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"space-bunny-alpha","messages":[{"role":"user","content":"YOUR_TEST_PROMPT"}]}'

Any OpenAI-compatible client works the same way: point the API base at https://tokenra.io/v1 and set the model ID to space-bunny-alpha.

import openai

client = openai.OpenAI(
    base_url="https://tokenra.io/v1",
    api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
    model="space-bunny-alpha",
    messages=[{"role": "user", "content": "YOUR_TEST_PROMPT"}],
)
print(response.choices[0].message.content)

Space Bunny Alpha pricing: $0.09 input, $0.36 output

Space Bunny Alpha costs $0.09 per 1M input tokens, $0.36 per 1M output tokens, and $0.009 per 1M cached input tokens through TokenRa, 40% below the MiniMax M3.1 Flash list price of $0.15 / $0.60 / $0.015. It was free until October 31, 2026. Rates can change without notice; access is also subject to account eligibility, provider availability, and applicable rate limits. Verify the live TokenRa console before production use.

What to watch out for

A low price does not remove operational tradeoffs, and an anonymous release adds two of its own. Review these points before depending on Space Bunny Alpha in production.

• Stealth codename, now claimed: MiniMax has identified Space Bunny as an early version of MiniMax M3.1 Flash, so this codename can be retired at any time. Plan a move to minimax-m3.1-flash and do not build the codename into your product surface.
• Provider confirmed: MiniMax's October 19, 2026 release post identifies Space Bunny as an early version of MiniMax M3.1 Flash. The specifications on this page describe the stealth release and can differ from the released model.
• Benchmarks: MiniMax publishes scores for the released MiniMax M3.1 Flash, not for this stealth build, so evaluate Space Bunny Alpha against your own workload rather than third-party claims.
• Structured output is not schema-enforced, so validate and repair JSON in your application.
• Video input behaviour should be verified on your account rather than assumed from the specification.
• Pricing can change; confirm rates and limits in the console before you depend on them.

What is known about its identity

Space Bunny Alpha appeared anonymously, but its identity is no longer an open question. On October 19, 2026 MiniMax released MiniMax M3.1 Flash and stated in the release post that Space Bunny was an early version of that model, run without a name while it processed roughly 200 trillion tokens.

That confirms what earlier evidence pointed to: independent fingerprint analysis of a same-codename model served through a different gateway had reported a MiniMax-family tokenizer, documented in our analysis Is Space Bunny Alpha MiniMax? Benchmarks, pricing and integration code for the released model are on the MiniMax M3.1 Flash API (released version) page.

Data handling stated for this preview

Prompts and completions are retained by the provider and are not used for training. The provider's own terms, now known to be MiniMax's, govern rather than TokenRa's. Review the applicable terms before sending sensitive or regulated information.

Production checklist

• Keep API keys on the server and separate credentials by environment.
• Confirm the 1M-token context and the supported input modalities against the live integration before relying on them.
• Do not build the codename space-bunny-alpha into your own API surface — keep it in configuration so moving to minimax-m3.1-flash is a config change, not a deploy.
• Evaluate representative long-context, multimodal, and agentic workloads on your own data.
• Set explicit timeouts, bounded retries, tracing, and application-side budgets.
• Configure a fallback model for availability gaps and for any change to pricing.
• Review data handling, provider terms, privacy requirements, and output rights for your use case.

Space Bunny Alpha API FAQ

Continue exploring