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...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.00000008 | $0.080 |
| completion | 0.00000013 | $0.130 |
| input_cache_read | 0.00000004 | $0.040 |
{
"temperature": 1,
"top_p": 0.95,
"top_k": 20
}