PrismML models

PrismML works on making capable models small enough to run cheaply. Zeplik carries Ternary Bonsai 2 27B, a reasoning model derived from Qwen3.8-27B and shrunk by ternary compression, which handles code, mathematics, tool calling and image understanding over a 262K window.

Ask a PrismML model now

All 1 PrismML model

Pricing at a glance

Frequently asked questions

Which PrismML models can I use on Zeplik?

Zeplik carries 1 PrismML model: Ternary Bonsai 2 27B. They all run in the same chat, so you do not need a separate PrismML account or API key.

How much do PrismML models cost on Zeplik?

Output tokens cost 6.0 credits per million (raw provider rate $0.50 per million). 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin.

Which PrismML model has the largest context window?

Ternary Bonsai 2 27B, at 262K tokens (262,144). The context window covers the conversation plus any documents you attach.

Do PrismML models support images and tool calling?

All 1 accept image input, and all of them support tool calling.

Do I need a paid plan to use PrismML models on Zeplik?

All 1 need a paid plan (Plus or above). Usage is then billed in credits from your monthly allowance.

What is the newest PrismML model on Zeplik?

Ternary Bonsai 2 27B, released September 2026. 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.

Other providers

• OpenAI (100)
• Qwen (53)
• Google (42)
• Anthropic (29)
• Mistral (26)
• Z.ai (18)
• DeepSeek (15)
• NVIDIA (11)
• All models