Anthropic Claude Haiku 5.5 vs PrismML Ternary Bonsai 2 27B
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Ternary Bonsai 2 27B is 1.1× cheaper at a typical mix of 3 input tokens per output token.
- Claude Haiku 5.5 accepts longer prompts: 1M vs 262K tokens.
| Claude Haiku 5.5 | Ternary Bonsai 2 27B | |
|---|---|---|
| Vendor | Anthropic | PrismML |
| Released | 2026-10-07 | 2026-09-18 |
| Input / 1M | $0.10 | $0.075 |
| Output / 1M | $0.50 | $0.50 |
| Cached input / 1M | $0.01 | $0.037 |
| Blended / 1M (3:1) | $0.20 | $0.181 |
| Context | 1M | 262K |
| Max output | 128K | 33K |
| Accepts | text, image, file | text, image |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 10 | 1 |
| Cheapest provider, output | $0.50 | $0.50 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | 1655 ±84 | not playing |
| Vendor API status | Operational | — |
Cost calculator
Claude Haiku 5.5
$13.50 per month$0.45 per day
Ternary Bonsai 2 27B
$12.00 per month$0.40 per day
Ternary Bonsai 2 27B saves $1.50 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Claude Haiku 5.5 with
Compare Ternary Bonsai 2 27B with