← Home
Space Bunny API pricing
Two models on one hosted, OpenAI-compatible API: Space Bunny Flash at $0.50/M for fast, budget work, and Space Bunny (Alpha) at $1.50/M for the 1M-context flagship. Try either free in the playground, then pay as you go from $5 — no subscription.
$0.50/M
Flash — per 1M tokens
$1.50/M
Alpha — per 1M tokens
$5
Minimum top-up
1M
Context window
MODELSPick a model with the standard
Pick a model with the standard model field
space-bunny-flash — fast, budget tier$0.50 / 1M tokensspace-bunny-alpha — 1M context, reasoning (default)$1.50 / 1M tokensBilled per total token (prompt + completion) at the chosen model’s rate. Omit model and you get Alpha.
PAY AS YOU GO
Prepaid credits
Top up from $5. Credits never expire; top up any time.
Buy credits — start in a minute
Pick a pack, pay with card, and your balance is topped up instantly. Credits never expire.
$5
≈ 3.3M input tokens
$1.50/M
$10
≈ 6.7M input tokens
$1.50/M
Popular
$20
≈ 13.3M input tokens
$1.50/M
Dev
$50
≈ 40.0M input tokens
$1.25/M
Production
$100
≈ 112.0M input tokens
$0.89/M
Secure checkout by Stripe · credits land on your account instantly · manage keys in the dashboard.
curl https://spacebunnymodel.com/api/v1/chat/completions \
-H "Authorization: Bearer sb_live_..." \
-H "Content-Type: application/json" \
-d '{
"model": "space-bunny-alpha",
"messages": [{ "role": "user", "content": "Hello, Space Bunny!" }]
}'Preview pricing is temporary. Pricing may change when the Space Bunny preview ends. We’ll show updated pricing before it applies to you.
What you get
- Space Bunny Alpha via an OpenAI-compatible endpoint — drops into any SDK, CLI or agent.
- A 1,000,000-token context window and up to 524,288 output tokens.
- Streaming, reasoning control, and multimodal input support.
- Self-serve keys, usage history and invoices in your dashboard.
How billing works
- Each call deducts
$1.50 / 1M total tokens(prompt + completion) from your balance. - When your balance runs out, top up from $5. No subscription, no monthly minimum — credits don’t expire.
- Each API key is limited to 30 requests per minute.