Ternary Bonsai 2 9B

by PrismMLprism-ml/ternary-bonsai-2-9b

  • Text
  • No route yet
  • Released

LLMCompare cannot run Ternary Bonsai 2 9B yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.

See the models that can be run now

Ternary Bonsai 2 9B at a glance

Context length
262,144 tokens
Maximum output
65,536 tokens
Accepts
Text, Image
Returns
Text
Features
JSON outputTool callingPrompt cachingImage input
Reasoning effort levels
Not supported
Released
16 Oct 2026
Knowledge cutoff
Not published

Model facts synced from the OpenRouter model list on 27 Oct 2026.

Ternary Bonsai 2 9B pricing by route

A route is the service LLMCompare calls to reach the model. Ternary Bonsai 2 9B has 1 route. Prices are in US dollars.

Prices of Ternary Bonsai 2 9B on each route
RouteOn LLMCompareInputper 1M tokensOutputper 1M tokensCache readper 1M tokensPrice verified onSource
OpenRouterDefaultNot configured$0.08$0.13$0.04openrouter.ai/prism-ml/ternary-bonsai-2-9b

The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.

Cost calculator

Estimate what a batch of calls to Ternary Bonsai 2 9B costs. The starting numbers are examples. Change them to match your task.

Part of the input tokens above, billed at the cache read price.

Cost per call
$0.00015
1 credits
Cost of 100 calls
$0.0145
100 credits

Calculated from the OpenRouter prices verified on 27 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.

Parameters you can set

These are the parameters LLMCompare can set when it calls the model through OpenRouter.

Parameters of Ternary Bonsai 2 9B
ParameterTypeRange or optionsDefault
temperatureNumber0 to 2in steps of 0.1Provider default
top_pNumber0 to 1in steps of 0.05Provider default
max_tokensInteger1 to 65,536Provider default
seedInteger-2,147,483,648 to 4,294,967,295Provider default
response_formatOne oftextjson_objectProvider default

About Ternary Bonsai 2 9B

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...

Description as published for this model. LLMCompare has not edited it.

Models to compare with Ternary Bonsai 2 9B

Text models from the same provider and models at the nearest price. The order is not a ranking.

Models to compare with Ternary Bonsai 2 9B
Add to comparisonModelContextMax outputInput priceper 1M tokensOutput priceper 1M tokensFeaturesReleasedOn LLMCompare
Ternary Bonsai 2 27BPrismMLprism-ml/ternary-bonsai-2-27b262k32.8k$0.075$0.50ReasoningJSONToolsCacheVisionNo route yet
Phi 4Microsoft AImicrosoft/phi-416.4k14.7k$0.07$0.14JSONNo route yet
Reka Edgerekaairekaai/reka-edge16.4k14.7k$0.10$0.10JSONToolsVisionNo route yet
Ministral 3 3B 2512Mistralmistralai/ministral-3b-2512131k105k$0.10$0.10JSONToolsCacheVisionNo route yet
Gemma 3 12BGooglegoogle/gemma-3-12b-it131k16.4k$0.05$0.15JSONToolsVisionNo route yet
Hy-MT2-1.8BTencenttencent/hy-mt2-1.8b8.2k4.1k$0.044$0.177—No route yet

Questions about Ternary Bonsai 2 9B

How much does Ternary Bonsai 2 9B cost?
On the OpenRouter route, Ternary Bonsai 2 9B costs $0.08 per 1 million input tokens and $0.13 per 1 million output tokens, in US dollars. Input tokens that Ternary Bonsai 2 9B reads from the prompt cache cost $0.04 per 1 million tokens. LLMCompare verified this price on 27 Oct 2026.
What is the context length of Ternary Bonsai 2 9B?
Ternary Bonsai 2 9B has a context length of 262,144 tokens and returns up to 65,536 output tokens in one call.
What inputs does Ternary Bonsai 2 9B accept?
Ternary Bonsai 2 9B accepts these inputs: Text, Image. Ternary Bonsai 2 9B returns: Text.
Can I test Ternary Bonsai 2 9B on my own data?
Not yet. LLMCompare lists the prices and parameters of Ternary Bonsai 2 9B, but no route to Ternary Bonsai 2 9B is configured on LLMCompare, so it cannot be selected for an evaluation.