Ternary Bonsai 2 27B
Ternary Bonsai 2 27B is a 27B-parameter reasoning model developed by PrismML based on Qwen3.8-27B. It is designed to handle complex tasks including coding, mathematics, and image analysis within a large 262,144-token context window.
Ternary Bonsai 2 27B specs and pricing
- Provider: PrismML
- Released: September 18, 2026
- Context window: 262K tokens
- Max output: 33K tokens
- Input: text, images
- Output: text
- Price: $0.075 input / $0.50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Ternary Bonsai 2 27B is good at
- Analyzing complex documents or codebases
- Solving multi-step mathematical problems
- Interpreting and extracting data from images
To-dos to try with Ternary Bonsai 2 27B
- Upload a technical diagram and ask the model to explain the workflow
- Paste a large codebase and request a list of potential security vulnerabilities
- Provide a long research paper and ask for a summary of the methodology and key findings
FAQ
- What types of input does Ternary Bonsai 2 27B support? The model accepts both text and image inputs.
- What are the primary capabilities of this model? It is capable of reasoning, coding, mathematics, tool calling, and image understanding.
- How much does Ternary Bonsai 2 27B cost? Ternary Bonsai 2 27B costs $0.075 per million input tokens and $0.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.28 credits ($1 = 100 credits).
- What is the context window of Ternary Bonsai 2 27B? Ternary Bonsai 2 27B can read up to 262K tokens at once and write up to 33K tokens in one reply.
- Can I use Ternary Bonsai 2 27B without coding? Yes. In todo.is you pick Ternary Bonsai 2 27B as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.