Salesforce launches Koa Decisions, a Gemma-based model that classifies text, image and audio requests
Salesforce introduced Koa Decisions on November 6, 2026. The decision model is built from Google's open-weight Gemma and accepts text, images and audio. It is the next version of HyperClassifier.
Salesforce introduced Koa Decisions on November 6, 2026, a decision model built from Google's open-weight Gemma that accepts text, images, and audio.
What Koa Decisions does
Koa Decisions is the next version of HyperClassifier. It reads a request and a user-defined list of categories, then returns one of three outputs in a single step: a selection, a yes-or-no decision, or a score.
Where it will be used
Salesforce plans to expand the technology beyond Agentforce request routing into Salesforce workflows and developer tools.
Details
- Release date: November 6, 2026
- Base model: Google's open-weight Gemma
- Input modalities: text, images, audio
- Outputs: a selection, a yes-or-no decision, or a score
- Predecessor: HyperClassifier
- Current use: Agentforce request routing
The source is a report from Unite.AI. Context window, pricing, parameter count and benchmark scores are not yet disclosed.
What this means
Koa Decisions extends HyperClassifier from text to image and audio inputs. Requests in those formats can now be classified against a user-defined category list in the same single step. Salesforce's stated plan to move the technology from Agentforce request routing into workflows and developer tools indicates the model is intended for broader use than routing alone.
Related Articles
Ant Group releases Ling-3.2-flash: 560B-parameter multimodal model with 1M-token context
Ant Group released Ling-3.2-flash on November 5, a native multimodal model that accepts text, images, and video. It has 560 billion total parameters, activates 25 billion per inference step, and supports a one-million-token context window.
Google releases Gemini Omni 1.2 Flash video model: 15-second clips up to 4K with native audio
Google released Gemini Omni 1.2 Flash on November 5, 2026, a native multimodal video generation and editing model that succeeds Gemini Omni 1.1 Flash. It generates clips up to 15 seconds with native audio at resolutions from 360p to 4K. OpenRouter lists it at $1.50 input and $9 output per 1M with a 131K context window.
Google releases Gemini Omni 1.1 Flash, a generally available video model with 4K output and native audio
Google released Gemini Omni 1.1 Flash on Nov 4, 2026, a native multimodal video generation and editing model that is the generally available successor to Gemini Omni Flash Preview. It outputs clips from 360p drafts up to 4K with native audio, and is listed on OpenRouter at $1.50 input / $9 output per 1M tokens with a 131K context window.
Underdog releases Woof, a 31M-parameter open text-to-speech model that runs in a browser
Underdog's new text-to-speech model Woof has 31 million parameters and weighs 31.7 MB. The company says it runs on most devices without an internet connection, and the weights are open to download. Underdog demonstrated it with a browser game posted on November 5, 2026.
Comments
Loading...