# Model Catalog

The Deka LLM service in the Service Portal offers 11 models. The following table lists the available Deka LLM models that can be used.

## Embeddings & Search

Models designed for semantic search, vector embeddings, and Retrieval Augmented Generation (RAG) use cases.

<table><thead><tr><th width="104">Provider</th><th width="280.68511962890625">Model</th><th>Description</th></tr></thead><tbody><tr><td>BAAI</td><td><strong>bge-multilingual-gemma2</strong></td><td>Vector embedding model for semantic search, similarity tasks, and text reranking (multilingual support).</td></tr><tr><td>Alibaba</td><td><strong>qwen3-embedding-4b</strong></td><td>Model designed to generate high-quality vector representations of text for semantic search, similarity matching, clustering, and Retrieval-Augmented Generation (RAG) applications.</td></tr></tbody></table>

## Text Generation

Models designed for chatbot and virtual assistant development, summarization, documentation generation, and general natural language processing (NLP) use cases.

<table><thead><tr><th width="126.6666259765625">Provider</th><th width="275.40740966796875">Model</th><th>Description</th></tr></thead><tbody><tr><td>Google</td><td><strong>gemma-3-27b-it</strong></td><td>Large language model for text generation, completion, and various NLP tasks (7B parameters). </td></tr><tr><td>Alibaba</td><td><strong>qwen25-72b-instruct</strong></td><td>Conversational AI model designed for interactive dialogue and instruction following (instruction-tuned).</td></tr><tr><td>Alibaba</td><td><strong>qwen3-30b-a3b-instruct-2507</strong></td><td>Conversational AI model designed for interactive dialogue and instruction following (instruction-tuned).</td></tr><tr><td>OpenAI OSS</td><td><strong>gpt-oss-20b</strong></td><td>Conversational AI model designed for interactive dialogue and instruction following (20B parameters).</td></tr><tr><td>GOTO</td><td><strong>sahabat-ai-v2-70b-it</strong></td><td>Large language model for text generation, completion, and various NLP tasks.</td></tr><tr><td>NVIDIA</td><td><strong>nemotron-3-nano-30b-a3b</strong></td><td>Optimized for text generation, conversational AI, and automation, offering efficient performance, low latency, and suitability for large-scale enterprise deployment.</td></tr><tr><td>OpenAI</td><td><strong>whisper-large-v3</strong></td><td>Large language model for text generation, completion, and various NLP tasks</td></tr></tbody></table>

## Vision & Multimodal

Models designed to process and understand multimodal inputs, including images and text.

<table><thead><tr><th width="129.11114501953125">Provider</th><th width="261.14813232421875">Model</th><th>Description</th></tr></thead><tbody><tr><td>Alibaba</td><td><strong>qwen25-vl-7b-instruct</strong></td><td>Conversational AI model designed for interactive dialogue and instruction following (instruction-tuned)</td></tr><tr><td>Meta</td><td><strong>llama-4-maverick-instruct</strong></td><td>Vision-language model capable of understanding and analyzing images with text (instruction-tuned)</td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.cloudeka.ai/guidance-for-individual/deka-llm/model-catalog.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.