PrismML: Ternary Bonsai 2 27B
The PrismML model is a ternary Bonsai 2 27B AI developed by prism-ml. It handles text and image input modalities within a context length of 262144 tokens and supports up to 32768 completion tokens. For users looking for an AI model that can handle both text and image inputs, PrismML may be worth considering due to its diverse input capabilities. However, it is not the cheapest option, with a price point of $0.075 per million input tokens and $0.5 per million output tokens. Without independent benchmark coverage, it's difficult to determine how well this model performs in real-world tasks; however, those who can afford its pricing may want to shortlist PrismML for further evaluation based on their specific needs.
- Model ID
- prism-ml/ternary-bonsai-2-27b
- Vendor
- prism-ml
- Released
- September 2026
- Tokenizer
- Qwen
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 32,768 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.07/M input and $0.50/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.06 |
| A month of a busy support chatbot | 5M in / 2M out | $1.38 |
Category rankings
Where PrismML: Ternary Bonsai 2 27B places across the 3 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #18 | Social Media PostsWriting · of 25 ranked | 119 |
| #18 | Voice Assistant BackendVoice · of 25 ranked | 123 |
| #25 | JSON ExtractionData · of 25 ranked | 131 |
Quick answers
- How much does PrismML: Ternary Bonsai 2 27B cost?
- $0.07 per million input tokens and $0.50 per million output tokens.
- What is PrismML: Ternary Bonsai 2 27B's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does PrismML: Ternary Bonsai 2 27B support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can PrismML: Ternary Bonsai 2 27B process images?
- Yes, it accepts image input.