about 0.01¢ a message
A typical message: about 500 tokens you send and 500 it writes.
$0.088 per 1M tokens you send$0.143 per 1M tokens it writesreads 262k tokens at once
About
Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...
In PrismML's words.
Try it here
Published facts
What the upstream's catalog says about this world, with its price as billed here.
- Context window
- 262,144 tokens
- Longest answer
- 65,536 tokens
- Input, per 1M tokens
- $0.088upstream $0.08
- Output, per 1M tokens
- $0.143upstream $0.13
- Cached input, per 1M
- $0.044upstream $0.04
- Margin
- +10%
- Reads
- text and images
- First listed
- 2026-10-16
Speed and reliability measured on this gateway join these once this world has served requests through Antimatter.
Price and latency history as JSON: GET /api/planet/history?id=prism-ml/ternary-bonsai-2-9b.
Call it
One OpenAI compatible endpoint, this model's id, and an am_live_ key from the dashboard. Or try it in chat first, no key needed.
curl https://useantimatter.com/v1/chat/completions \
-H "Authorization: Bearer $ANTIMATTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "prism-ml/ternary-bonsai-2-9b", "messages": [{"role": "user", "content": "Hello"}]}'Everything else is in the docs.
Embed this
A badge with this world's live price per million tokens, as billed here, for a README or a site. It links back to this page.
<a href="https://useantimatter.com/planet/prism-ml/ternary-bonsai-2-9b"><img src="https://useantimatter.com/api/badge/price?id=prism-ml%2Fternary-bonsai-2-9b" alt="Ternary Bonsai 2 9B price on Antimatter" height="28"></a>More from PrismML
Similar worlds, other makers
Closest in price and memory, from other vendors.
Head back to the galaxy, or carry this world into a thread.