Provider

PPrism Ml

Every Prism Ml model UltraGPT can reach, kept in sync with the live catalog — pricing, context window and capabilities for each one.

2 models from Prism Ml Up to 262.1K tokens of context
Open the appBrowse every provider

2

Models tracked

1

Providers

2

Reasoning models

2

See images (vision)

262K

Largest context window

0

Free to run

Directory

All Prism Ml models.

Search and filter this provider's lineup — pricing per million tokens, context window, modalities, reasoning effort and independent benchmark scores where available.

2 of 2 models

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...

ReasoningTool callingVisionStreamingJSON mode
Context window262.1K tok
Max output32.8K tok
ReleasedSep 18, 2026
Knowledge cutoff—
Text + ImageText
Input$0.075 / 1M tok
Output$0.5 / 1M tok
Cache read$0.037 / 1M tok
Effort: xhigh, medium, none

Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...

ReasoningTool callingVisionStreamingJSON mode
Context window262.1K tok
Max output65.5K tok
ReleasedOct 16, 2026
Knowledge cutoff—
Text + ImageText
Input$0.08 / 1M tok
Output$0.13 / 1M tok
Cache read$0.04 / 1M tok

Every Prism Ml model above, one subscription away.

UltraGPT puts this whole directory behind a single login and one flat monthly price — no separate bill per provider.