Space Bunny

A new signal from the unknown

Space Bunny.Big context. Curious mind.

Meet an anonymous reasoning model with a one-million-token context window, text, image and video input, and adjustable reasoning.

Try Space BunnyExplore the API
Token context window
Maximum completion tokens
Input types: text, image and video
Current preview price per 1M tokens
prompttext

Review this production incident, identify the likely root cause, and propose the safest recovery plan.

Prompt sent to Space Bunny

Space Bunny

Multimodal reasoning model

context_windowcontext1M
1.00
reasoning_effortreasoninghigh
0.80
outputmodalitytext
1.00

// Illustrative capability signals. Run your own prompt in the playground below.

Send a signal into deep space

Chat with Space Bunny. Adjust reasoning effort, request JSON, or add a public image or video URL.

Usage-based credits

Space Bunny Playground

space-bunny

1M context · text, image and video input

What should the bunny investigate?

Ask an open-ended question, review code, reason across a long document, or attach a public image or video URL.

Try a field test

One request. A very large working memory.

Keep the model call on your server, choose the reasoning effort for the job, and send text or multimodal context in the standard chat format.

  1. 01

    Bring the context

    Send a prompt alone, a long document, source code, an image URL or a compatible video URL.

    ❯ messages = [{ role: 'user', content }]
  2. 02

    Set the reasoning effort

    Start at low for everyday work, then raise the effort when a task benefits from deeper reasoning.

    ❯ reasoning = { effort: 'low' }
  3. 03

    Use the response

    Render the answer, request JSON, or connect tool calls while your application keeps authority over side effects.

    ❯ answer = response.choices[0].message

Long-context reasoning for real work.

Use Space Bunny for coding, research, visual understanding and agent workflows through one consistent API.

reasoning = { effort: selected }

low0.20
medium0.45
high0.78
max1.00

A million tokens of context

Work across long documents, large repositories and extended sessions without fragmenting the task into tiny pieces.

82%

GPQA Diamond · field test

Five reasoning levels

Choose low, medium, high, xhigh or max reasoning effort to match the task's speed and depth.

prompt
  • text
  • image
  • video
  • tools

Text, images and video

Ask about source code, screenshots, diagrams or video and receive a text response in the same conversation.

tools = [get_file, search_records]
response = chat({ model, messages, tools })
await execute_approved(response.tool_calls)

Built for tool use

Give the model functions and let it request the right tool with structured arguments.

$ curl -X POST /api/v1/chat/completions
  -H "Authorization: Bearer sk_…"

200 OK · 118ms

Developer-friendly API

Use the familiar chat completions format, optional JSON responses and standard usage metadata.

An independent field guide

Explore current capabilities, model details, API examples and practical boundaries before you ship.

textimagevideotoolsjson

A long-context model for more than chat

Space Bunny combines coding, multimodal input, tool calling and adjustable reasoning in one model endpoint.

review.py
response = client.chat.completions.create(
    model="space-bunny",
    messages=[{"role": "user", "content": repo_context}],
    extra_body={"reasoning": {"effort": "high"}},
)

review = response.choices[0].message.content

// trace

  • context_window1,000,000
  • reasoning_efforthigh

Connect your product to Space Bunny

Use a familiar chat request format for text, multimodal context, structured output and tool calls. Keep every API key on the server.

  • OpenAI-compatible REST
  • Streaming, JSON and tools
  • Server-side API keys
Explore integration docs
chat.pyPOST /api/v1/chat/completions
from openai import OpenAI

client = OpenAI(
    base_url="https://spacebunny.app/api",
    api_key=SPACE_BUNNY_API_KEY,
)

response = client.chat.completions.create(
    model="space-bunny",
    messages=[{
        "role": "user",
        "content": "Review this design"
    }],
    extra_body={"reasoning": {"effort": "low"}},
)

# response.choices[0].message.content

A minimal request — Change reasoning effort without changing endpoints

setup.shSpace Bunny · Agent-ready
# Configure an OpenAI-compatible client

# 1. endpoint
export SPACE_BUNNY_API_URL="https://spacebunny.app/api"

# 2. configure
export SPACE_BUNNY_API_KEY="sk_your_key_here"
export OPENAI_MODEL="space-bunny"

Your application keeps control

The model can request a tool call, but your code still validates permissions, arguments, side effects and human approval boundaries.

Give your agent more room to think

Connect Space Bunny to your agent stack and choose the reasoning effort for each task.

  1. 1

    Use the Space Bunny endpoint

    Connect your client to the Space Bunny API and use the chat request format your agent already understands.

  2. 2

    Keep the key server-side

    Store the API key in your server environment and never expose it in browser code or public prompts.

  3. 3

    Offer only approved tools

    Define the functions your agent may request, then validate arguments and permissions before execution.

Read the API guide

From first prompt to a production Space Bunny call

Start with the model ID and message format, then add multimodal input, reasoning controls, tools and structured output.

Open full docs
/docs

Quickstart

Create an API key, send your first chat request, and read the returned assistant message.

/docs

Add multimodal input

Mix text with an image_url or video_url content part when the task needs visual context.

/docs

Control reasoning

Choose low, medium, high, xhigh or max reasoning effort for the speed and depth your task needs.

/docs

Know the boundaries

The model is anonymous and in preview. Architecture, parameter count, training details and knowledge cutoff are not disclosed.

Plans and usage

Space Bunny Pricing

Start free in the playground, then choose a permanent credit pack when you are ready for more Space Bunny usage.

One-time purchase. No subscription, no auto-renewal, and credits never expire.

Try Space Bunny before you buy

The playground preview is free. Test text, image and video prompts, adjust reasoning effort, and confirm the model fits your workflow before purchasing credits.

Open free playground

Starter

$9.9

100,000 permanent credits for experiments, prototypes and your first integration

  • 100,000 credits, no expiry
  • 1 workspace
  • 1 concurrent request
  • Standard speed
  • Text, image and video prompts
  • Text and JSON output
  • Adjustable reasoning effort
  • Online playground
  • API key management
  • Email support
Recommended

Pro

$99

1,000,000 permanent credits for regular long-context, multimodal and tool workflows

  • 1,000,000 credits, no expiry
  • Unlimited workspaces
  • 3 concurrent requests
  • Fast lane
  • Text, image and video prompts
  • Text and JSON output
  • Long-context conversations
  • API access
  • Usage and request history
  • Priority support

Enterprise

$999

11,000,000 permanent credits, including 10% extra, for teams and high-volume workloads

  • 11,000,000 credits, no expiry (10% extra included)
  • Everything in Pro
  • 10 concurrent requests
  • Dedicated fast lane
  • Team workspaces and collaboration
  • Custom integration support
  • Security and permission guidance
  • Dedicated support
  • Priority production processing
  • Product roadmap feedback

FAQ

Questions, answered

A few quick answers before you try Space Bunny.

A million tokens. One curious bunny.

Try Space Bunny with a real prompt, tune the reasoning effort, then connect the same workflow to your product.

Open the playground