Ternary Bonsai 2 27B
Ternary Bonsai 2 27B is a large language model made by PrismML, added to the catalog on 18 Sep 2026. It has a context window of 262,144 tokens and costs $0.075 per 1M input tokens and $0.50 per 1M output tokens. It accepts text and images and produces text. Typical uses: reasoning over long text inputs, coding assistance and mathematical problem solving.
Price checked ยท source: OpenRouter
What Ternary Bonsai 2 27B is
PrismML: Ternary Bonsai 2 27B is a reasoning model derived from Qwen3.8-27B. It accepts text and image inputs and produces text. Its listed capabilities include coding, mathematics, tool calling, and image understanding. It also supports reasoning, tools, structured outputs, and response-format settings. These features make it suitable for requests that combine text with image input or call for a specified structure in the text response.
The model has a context window of 262,144 tokens and can produce up to 32,768 output tokens. Its context capacity suits tasks involving extensive input, including requests that bring together long passages or multiple pieces of material. The output limit allows for substantial text responses, while the available response-format and structured-output features support requests that specify how text should be organized. The catalog does not give details about particular output formats or tools.
Bonsai 2 27B is intended for work involving reasoning, coding, and mathematics, as well as image understanding. Tool calling provides support for workflows that use tools, and text output can be used for explanations, answers, or other written results. The combination of text and image input makes image-related requests possible alongside text-based work. Its large context window may be relevant when a task requires the model to consider a substantial amount of input in one request. The listed facts describe supported modalities and capabilities but do not specify particular applications, tools, or image types.
Key features
- Accepts text and image inputs and produces text
- Has a 262,144-token context window
- Supports reasoning, tool calling, structured outputs, and response formats
- Supports coding, mathematics, and image understanding
- Can produce up to 32,768 output tokens
Typical uses
- Reasoning over long text inputs
- Coding assistance
- Mathematical problem solving
- Image understanding
- Tool-assisted workflows
- Structured text generation
Ternary Bonsai 2 27B pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.075 |
| Output, per 1M tokens | $0.50 |
| Cached input read, per 1M tokens | $0.0375 |
No price change since it was added on 18 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0002 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0023 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0033 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.012 |
Ternary Bonsai 2 27B specifications
| Model id | prism-ml/ternary-bonsai-2-27b |
|---|---|
| Version | ternary-bonsai-2-27b-20260918 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 32,768 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 18 Sep 2026 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| 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 27B yet.
Compare Ternary Bonsai 2 27B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.