Ternary Bonsai 2 27B vs Ternary Bonsai 2 9B
Ternary Bonsai 2 27B (PrismML) and Ternary Bonsai 2 9B (PrismML) are listed at different prices. Ternary Bonsai 2 27B costs less for input, $0.075 per 1M tokens against $0.08; Ternary Bonsai 2 9B costs less for output, $0.13 per 1M tokens against $0.50. Both hold 262,144 tokens of context. Only Ternary Bonsai 2 27B supports a reasoning effort setting. Both accept text and images and produce text.
PrismML: Ternary Bonsai 2 27B and PrismML: Ternary Bonsai 2 9B both accept text and images, produce text, support tools, structured outputs, response formats, and reasoning, and have 262,144-token context windows. Their maximum output lengths differ: 32,768 tokens and 65,536 tokens, respectively.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Ternary Bonsai 2 27B | Ternary Bonsai 2 9B |
|---|---|---|
| Maker | PrismML | PrismML |
| Added to catalog | 18 Sep 2026 | 16 Oct 2026 |
| Input, per 1M tokens | $0.075 | $0.08 |
| Output, per 1M tokens | $0.50 | $0.13 |
| Cached input read, per 1M | $0.0375 | $0.04 |
| Context windowTokens | 262,144 | 262,144 |
| Max outputTokens | 32,768 | 65,536 |
| Accepts | image, text | image, text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | Yes | No |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Ternary Bonsai 2 27B | Ternary Bonsai 2 9B |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0002 | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0023 | $0.0021 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0033 | $0.0027 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.012 | $0.012 |
Which to choose
Choose Ternary Bonsai 2 27B if
- Input tokens cost less: $0.075 against $0.08 per 1M
- Cached input costs less: $0.0375 against $0.04 per 1M
- You want to set how much it reasons before it answers
Choose Ternary Bonsai 2 9B if
- Output tokens cost less: $0.13 against $0.50 per 1M
- You need longer answers in one response: 65,536 tokens against 32,768
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.