PrismML: Ternary Bonsai 2 9Bprism-ml
Bottom Line
PrismML: Ternary Bonsai 2 9B: $0.08/1M input, $0.13/1M output, 262K context. Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...
API Pricing (per 1M tokens)
| Input | $0.08 |
| Output | $0.13 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.09 |
Specs & Performance
| Context Length | 262K |
| Max Output | 66K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text, image → text |
More from prism-ml
PrismML: Ternary Bonsai 2 9B vs rivals
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the PrismML: Ternary Bonsai 2 9B API cost?
PrismML: Ternary Bonsai 2 9B costs $0.08/1M input tokens and $0.13/1M output tokens. Blended cost at a 3:1 ratio is about $0.09/1M tokens.
What is the context window of PrismML: Ternary Bonsai 2 9B?
PrismML: Ternary Bonsai 2 9B supports a 262K token context window with up to 66K output tokens.
Is PrismML: Ternary Bonsai 2 9B worth it?
PrismML: Ternary Bonsai 2 9B has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.