← All models
PrismML · Language model
Ternary Bonsai 2 9B
prism-ml/ternary-bonsai-2-9b- Language
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...
Specifications
- Context window
- 262,144 tokens
- Max output
- 65,536 tokens
- Input
- text, image
- Output
- text
- Reasoning
- supported
- Tokenizer
- Qwen
Supported parameters
Accepted by the model and forwarded as-is by the gateway.
- frequency_penalty
- logprobs
- max_tokens
- presence_penalty
- reasoning
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Use it
POST /api/v1/chat/completions · MCP chat · full reference
curl https://omnirail.org/api/v1/chat/completions \
-H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
-d '{"model":"prism-ml/ternary-bonsai-2-9b","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'