Ternary Bonsai 2 27B
General purposeVisionToolsPrismML · Released September 2026
Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window.
It belongs to PrismML's Ternary Bonsai line, open models compressed to ternary weights to cut the cost of serving them.
Facts and pricing
- Provider
- PrismML
- Context window
- 262K tokens
- Input price
- 0.90 credits / 1M tokens ($0.075 raw)
- Output price
- 6.0 credits / 1M tokens ($0.50 raw)
- Vision (image input)
- Yes
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.
Try Ternary Bonsai 2 27B now
What Ternary Bonsai 2 27B is best for
- Balanced everyday work: writing, questions, brainstorming and summarization
- Long documents: the 262K-token window holds lengthy reports, contracts or papers whole
- Working with images: screenshots, charts, photos and scanned documents alongside text
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a general purpose model like Ternary Bonsai 2 27B:
- Help me outline a talk about what I learned this year
- Compare these two paragraphs and tell me which is clearer and why
- Draft a polite reply declining this invitation
- Explain this concept with a concrete everyday analogy
PrismML family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Ternary Bonsai 2 9B | 262K | 0.96 | 1.6 | October 2026 |
| Ternary Bonsai 2 27B | 262K | 0.90 | 6.0 | September 2026 |
Model comparisons
- Claude Fable 5.2 vs Claude Fable 5.1
- Claude Opus 5.5 vs Claude Fable 5.2
- GPT-6 Astra vs Claude Fable 5.2
- Claude Opus 5.5 vs Claude Opus 5
Frequently asked questions
- What is Ternary Bonsai 2 27B?
- Ternary Bonsai 2 27B is an AI model by PrismML. Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window.
- How much does Ternary Bonsai 2 27B cost on Zeplik?
- Input tokens cost 0.90 credits per million and output tokens 6.0 credits per million (1 credit = $0.10; the raw provider rates are $0.075 and $0.50 per million). New accounts start with free credits.
- How long can a conversation with Ternary Bonsai 2 27B be?
- Ternary Bonsai 2 27B has a 262K-token context window (262,144 tokens), which covers the conversation plus any documents you attach.
- Does Ternary Bonsai 2 27B support images and tools?
- Ternary Bonsai 2 27B accepts image input and supports tool calling.
Related models
Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use.
Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE).
DaisyRose 27B is an open-weight multimodal reasoning model from RadixArk, trained from [Qwen3.8 27B](https://openrouter.ai/qwen/qwen3.8-27b) using reinforcement learning only on long-horizon agent tasks, with no supervised fine-tuning or distillation.
Pixtral Large 2502 is the February 2025 version of Mistral AI's large multimodal model, following [Pixtral Large 2411](https://openrouter.ai/mistralai/pixtral-large-2411).
Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work.
GPT-6.2 Astra Pro is the same underlying model as [GPT-6.2 Astra](https://openrouter.ai/openai/gpt-6.2-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.
More you can do with Ternary Bonsai 2 27B
- 468 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Ternary Bonsai 2 27B or any model you pick.
- 1582 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.