Ternary Bonsai2 9B
ternary-bonsai-2-9b
Ternary Bonsai2 9B is Prism ML’s open-weight model derived from Qwen3.5-9B with ternary language weights. It accepts text and generates text, supports reasoning and tool calling, and offers a shared 262,144-token context window with up to 65,536 output tokens. Thinking is enabled by default and can be turned off.
Specification
most-agreed values
Context
262K
Max output
66K
Released
2026-10-23
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.08
Output
$0.13
Cache read
$0.04
Available from 3 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| kilo · prism-ml | $0.08 | $0.13 | $0.04 | — | 262K | 66K | — |
| nano-gpt · prism-ml | $0.08 | $0.13 | $0.04 | — | 262K | 66K | — |
| openrouter · prism-ml | $0.08 | $0.13 | $0.04 | — | 262K | 66K | — |
