How do I use Prism Ml models through the OpenRouter API?

OpenRouter serves 1 Prism Ml model behind one OpenAI-compatible API. Create an OpenRouter API key, point your client at https://openrouter.ai/api/v1, and set the model to an ID such as prism-ml/ternary-bonsai-2-27b. The quickstart has request examples for every supported SDK.

Which Prism Ml model has the largest context window?

Ternary Bonsai 2 27B has the largest context window of any Prism Ml model on OpenRouter, accepting up to 262,144 tokens per request.

What is the newest Prism Ml model on OpenRouter?

Ternary Bonsai 2 27B is the most recently added Prism Ml model on OpenRouter, listed on September 18, 2026.

Prism Ml

Access 1 Prism Ml model through the OpenRouter unified API including Ternary Bonsai 2 27B. Compare pricing, context windows, benchmarks, and capabilities between different Prism Ml models.

Prism Ml tokens processed on OpenRouter

PrismML: Ternary Bonsai 2 27BTernary Bonsai 2 27B
4.95M tokens
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 the language-model weights to roughly 8.5 GB while retaining 98.2% of the base model's average score across PrismML's 14 thinking-mode benchmarks, enabling efficient inference on consumer hardware. The model thinks by default and defaults to xhigh reasoning effort.
by prism-mlSep 18, 2026262K context$0.075/M input tokens$0.50/M output tokens

Prism Ml

Access 1 Prism Ml model through the OpenRouter unified API including Ternary Bonsai 2 27B. Compare pricing, context windows, benchmarks, and capabilities between different Prism Ml models.

Prism Ml tokens processed on OpenRouter

PrismML: Ternary Bonsai 2 27BTernary Bonsai 2 27B
4.95M tokens
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 the language-model weights to roughly 8.5 GB while retaining 98.2% of the base model's average score across PrismML's 14 thinking-mode benchmarks, enabling efficient inference on consumer hardware. The model thinks by default and defaults to xhigh reasoning effort.
by prism-mlSep 18, 2026262K context$0.075/M input tokens$0.50/M output tokens

Prism Ml

Frequently asked questions

Prism Ml

Frequently asked questions