Available Model

The Deka LLM service in the Service Portal offers 15 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.

Provider	Model	Description
BAAI	bge-multilingual-gemma2	Vector embedding model for semantic search, similarity tasks, and text reranking (multilingual support).
Alibaba	qwen3-embedding-4b

Code Assistant

Models designed to support coding, scripting, automation, and overall developer productivity.

Provider	Model	Description
ZAI	glm-4.7-fp8	Large language model for text generation, completion, and various NLP tasks.

Text Generation

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

Provider	Model	Description
Meta	llama-3.3-70b-instruct	Conversational AI model designed for interactive dialogue and instruction following (instruction-tuned).
Meta	llama-3.1-70b-instruct	Conversational AI model designed for interactive dialogue and instruction following (instruction-tuned).
Google	gemma-3-27b-it	Large language model for text generation, completion, and various NLP tasks (7B parameters).
Alibaba	qwen25-72b-instruct	Conversational AI model designed for interactive dialogue and instruction following (instruction-tuned).
Alibaba	qwen25-vl-7b-instruct	Vision-language model capable of understanding and analyzing images with text (instruction-tuned, 7B parameters).
Alibaba	qwen3-32b	Large language model for text generation, completion, and various NLP tasks.
Alibaba	qwen3-30b-a3b-instruct-2507	Conversational AI model designed for interactive dialogue and instruction following (instruction-tuned).
OpenAI OSS	gpt-oss-20b	Conversational AI model designed for interactive dialogue and instruction following (20B parameters).
GOTO	sahabat-ai-v2-70b-it	Large language model for text generation, completion, and various NLP tasks.
NVIDIA	nemotron-3-nano-30b	Optimized for text generation, conversational AI, and automation, offering efficient performance, low latency, and suitability for large-scale enterprise deployment.

Vision & Multimodal

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

Provider	Model	Description
Alibaba	qwen25-vl-7b-instruct	Conversational AI model designed for interactive dialogue and instruction following (instruction-tuned)
Meta	llama-4-maverick-instruct	Vision-language model capable of understanding and analyzing images with text (instruction-tuned)