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...
With CoreAI, you can start chatting with PrismML: Ternary Bonsai 2 9B instantly — no separate subscription needed. CoreAI lets you chat with PrismML: Ternary Bonsai 2 9B alongside 300+ other AI models from Prism-ml and other providers like OpenAI, Anthropic, Google, Meta, and more.
PrismML: Ternary Bonsai 2 9B holds the #229 spot for context size out of 438 chat models in the CoreAI catalog — 262K tokens, roughly 196,608 words or 393 pages of text in a single conversation. On price, it is the #54 cheapest of 145 budget-tier models by input cost. Released 2026-10-16, it is one of the 13 newest additions to the catalog. It supports step-by-step reasoning (thinking mode) and accepts image input.
Every model in this table is available on CoreAI — open the web app and run the same prompt through PrismML: Ternary Bonsai 2 9B and PrismML: Ternary Bonsai 2 27B side by side to judge with your own eyes.
A typical question (about 1,000 tokens in, 500 out) runs $0.00015 on PrismML: Ternary Bonsai 2 9B's raw per-token rates; a heavy session with a 50K-token document costs about $0.005. On CoreAI you don't juggle these numbers — one subscription covers PrismML: Ternary Bonsai 2 9B and 300+ other models under a plan usage limit, with no API keys. See plans.
PrismML: Ternary Bonsai 2 9B handles 262K tokens of context — roughly 196,608 words, or about 393 pages of text in one conversation.
PrismML: Ternary Bonsai 2 9B's underlying rates are $0.08 per 1M input tokens and $0.13 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.
Yes — PrismML: Ternary Bonsai 2 9B accepts image input, so you can attach screenshots, photos or diagrams and ask questions about them.
Yes. PrismML: Ternary Bonsai 2 9B can work through problems step by step before answering; on CoreAI you can toggle thinking mode per message.
Open the CoreAI web app or the iOS/Android app, pick PrismML: Ternary Bonsai 2 9B in the model selector, and chat — no API key, no per-token billing. One subscription covers PrismML: Ternary Bonsai 2 9B and 300+ other models.
The closest alternatives on CoreAI are PrismML: Ternary Bonsai 2 27B, Recursive: Flint (free), Z.ai: GLM 5.2 — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.
Chat with PrismML: Ternary Bonsai 2 9B and 300+ other AI models — all in one app.