prism-ml
PrismML: Ternary Bonsai 2 27B
prism-ml/ternary-bonsai-2-27b
For $1, you can send approximately:
~248messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.07/M = $0.000525
Output cost per message7,000 x $0.50/M = $0.003500
Total cost per message$0.004025
Messages for $1248.45
Context window
262k
tokens
Max response
33k
tokens
Input price
$0.07
per million tokens
Output price
$0.50
per million tokens
Modalities
Input:textInput:imageOutput:text
Description
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. Ternary compression shrinks...