RentGPU RentGPU
寻找 GPU →
by Prism ML

PrismML: Ternary Bonsai 2 27B.

multimodal closed 262K ctx
Cheapest input
$0.075/M
on OpenRouter
Cheapest output
$0.5/M
on OpenRouter
Hosted equiv.
~$0.18/hr
@ 100 tok/s on OpenRouter

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.

Hosted API only

No self-host path — closed weights.

PrismML: Ternary Bonsai 2 27B's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $0.075 $0.5 Launch ↗
Sources

Official references.

Hugging Face ↗
FAQ

Frequently asked.

How do I run PrismML: Ternary Bonsai 2 27B?
PrismML: Ternary Bonsai 2 27B is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access PrismML: Ternary Bonsai 2 27B?
PrismML: Ternary Bonsai 2 27B is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run PrismML: Ternary Bonsai 2 27B?
API pricing starts at $0.075/M input tokens and $0.5/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is PrismML: Ternary Bonsai 2 27B open-source or proprietary?
PrismML: Ternary Bonsai 2 27B is a proprietary model from Prism ML. Access is API-only — there are no public weights to download.