Ternary Bonsai 2 9B
Ternary Bonsai 2 9B is a large language model made by PrismML, added to the catalog on 16 Oct 2026. It has a context window of 262,144 tokens and costs $0.08 per 1M input tokens and $0.13 per 1M output tokens. It accepts text and images and produces text. Typical uses: conversational assistance, reasoning and question answering and answering questions about images.
Price checked · source: OpenRouter
What Ternary Bonsai 2 9B is
Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. It accepts text and images and produces text. Its stated design uses ternary weights packed into 2 bits. The model also supports reasoning and tools, alongside structured outputs and response-format controls, for tasks that need more than a plain text exchange.
The model has a context length of 262,144 tokens and a maximum output length of 65,536 tokens. That context can accommodate lengthy prompts or substantial source material in a single interaction, while the output limit allows for extended responses when a task calls for them. These limits may suit work that involves examining long documents, combining information from several text passages, or developing a detailed response from a large prompt.
Text and image input make the model suitable for tasks that combine written instructions with visual material, such as asking questions about an image and receiving a written response. Its conversational and reasoning capabilities also fit general question answering and analysis. Tool support is relevant to workflows where the model uses available tools as part of a task, while structured-output support can help when a response needs to follow a defined format. The facts describe its supported capabilities but do not specify particular tools or output schemas.
Key features
- Accepts text and image input and produces text
- Supports a context length of 262,144 tokens
- Supports a maximum output of 65,536 tokens
- Supports tools, reasoning, structured outputs, and response formats
- Uses ternary weights packed into 2 bits
Typical uses
- Conversational assistance
- Reasoning and question answering
- Answering questions about images
- Analysis of lengthy documents
- Tool-supported workflows
- Producing structured text
Ternary Bonsai 2 9B pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.08 |
| Output, per 1M tokens | $0.13 |
| Cached input read, per 1M tokens | $0.04 |
No price change since it was added on 16 Oct 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0021 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0027 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.012 |
Ternary Bonsai 2 9B specifications
| Model id | prism-ml/ternary-bonsai-2-9b |
|---|---|
| Version | ternary-bonsai-2-9b-20261015 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 65,536 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 16 Oct 2026 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Ternary Bonsai 2 9B yet.
Compare Ternary Bonsai 2 9B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.