Skip to content
Alpha
  • Models
  • Rankings
  • Ori

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • EU routing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Customers
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for prism-mlFavicon for prism-ml

PrismML: Ternary Bonsai 2 9B

prism-ml/ternary-bonsai-2-9b

Model weights
Compare

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 inference. It accepts text and image input. Its 262K-token context window supports long conversations and document-heavy workflows, with up to 64K output tokens per response.

Modalities
In / Out Price
$0.08 / $0.13per 1M
Context
262K
Released
Oct 16, 2026
Compare
ProvidersPricingPerformanceUptimeAppsActivityFAQExplore

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
Latency / throughput
$0.08$0.13$0.040.67s51 tps
100.00%
Throughput
51tok/s

P50, best across providers

Latency
0.67s

P50, best provider

Uptime (3d)The model was reachable. Request routed to a provider.
98.40%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
95.21%

Availability over the last 3 days

Last 72 hours
Availability 95.21%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.38%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

1.
Favicon for http://model-radar/
model-radar
new
102Ktokens
2.
Favicon for https://cupid-router.dev/
Cupid Router Eval
new
14Ktokens
3.
Favicon for https://claude.ai/apple-touch-icon.png
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
13Ktokens
4.
Favicon for https://hellohaven.ai/
Hello Haven
new
12Ktokens
5.
Favicon for https://christus-nectere.local/homunculus
AOM
new
12Ktokens

Frequently asked questions

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 inference. It accepts text and image input. Its 262K-token context window supports long conversations and document-heavy workflows, with up to 64K output tokens per response.

Ternary Bonsai 2 9B costs $0.08/M input tokens and $0.13/M output tokens, with separate rates for Cache Read at $0.04/M tokens.

Ternary Bonsai 2 9B has a 262,144 token context window. It supports up to 65,536 completion tokens.

Yes. Ternary Bonsai 2 9B accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Ternary Bonsai 2 9B accepts text and images as input and returns text.

Ternary Bonsai 2 27B is another text model from PrismML.

Ternary Bonsai 2 9B was released on October 16, 2026.

More models from PrismML

Ternary Bonsai 2 27B

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.

Text262K context$0.075 / $0.50