PrismML: Ternary Bonsai 2 9B
PrismML's Ternary Bonsai 2 9B, from vendor prism-ml, accepts both text and image input. It offers a context window of 262,144 tokens and can produce up to 65,536 tokens in a single completion, which leaves room for long documents and extended outputs. The model supports tool calling and reasoning. The available facts do not indicate whether it offers structured output, and its open-weights status is also unspecified. Pricing is $0.08 per million input tokens and $0.13 per million output tokens, with only a small gap between input and output rates. The model has no independent benchmark coverage yet, so its quality relative to alternatives is unproven. It belongs on the shortlist for cost-sensitive teams that need long context, image input, and tool use in one model. Those teams should run their own evaluations on representative tasks before committing production traffic.
- Model ID
- prism-ml/ternary-bonsai-2-9b
- Vendor
- prism-ml
- Released
- October 2026
- Tokenizer
- Qwen
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 65,536 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 $0.08/M input and $0.13/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 | $0.05 |
| A month of a busy support chatbot | 5M in / 2M out | $0.66 |
Strong choice for
Category rankings
Where PrismML: Ternary Bonsai 2 9B places across the 5 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #1 | Social Media PostsWriting · of 25 ranked | 120 |
| #1 | Voice Assistant BackendVoice · of 25 ranked | 124 |
| #1 | Real-Time ChatLatency · of 25 ranked | 118 |
| #6 | Cheap Bulk InferenceCost · of 25 ranked | 137 |
| #7 | Self-Hosted / LocalCost · of 25 ranked | 117 |
Similar models
Quick answers
- How much does PrismML: Ternary Bonsai 2 9B cost?
- $0.08 per million input tokens and $0.13 per million output tokens.
- What is PrismML: Ternary Bonsai 2 9B's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does PrismML: Ternary Bonsai 2 9B support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can PrismML: Ternary Bonsai 2 9B process images?
- Yes, it accepts image input.