Ternary Bonsai 2 27B
PrismML · released 18 Sept 2026
Input$0.075per 1M tokens
Output$0.5per 1M tokens
Context262Ktokens
WeightsOpen
context on a 1K–2M scale
About
Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window.
Details
- Lab
- PrismMLopenrouter.ai · 3 Oct 2026
- Context
- 262Kopenrouter.ai · 3 Oct 2026
- Input price
- $0.075 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $0.5 / 1Mopenrouter.ai · 3 Oct 2026
- Max output
- 32,768 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- text, imageopenrouter.ai · 3 Oct 2026
- Open weights
- Yesopenrouter.ai · 3 Oct 2026
More longest-context models
See the listListed on Inferse
- Longest-Context Models in 2026466 listed
- Newest Models in 2026466 listed
- Cheapest Language Models in 2026444 listed
- Models with Tool Calling in 2026398 listed
- Reasoning Models in 2026332 listed
- Vision Language Models in 2026295 listed
- Open-Weight Models in 2026178 listed
Sources
- openrouter.ai/prism-ml/ternary-bonsai-2-27b· checked 3 Oct 2026


