AI Model Catalogue

A 17-billion parameter model with 128 experts and 262K token context window designed for developers and researchers who need efficient long-document processing, complex reasoning, and cost-effective inference across diverse language tasks.

A large language model with 164K token context designed for researchers, developers, and enterprises requiring advanced reasoning, long-document analysis, and complex problem-solving across technical, creative, and analytical domains.

A powerful open-source language model with 66K token context window designed for developers and researchers who need advanced instruction-following capabilities, multilingual support, and efficient processing of long documents across complex reasoning, code generation, and content creation tasks.

This compact language model with 41K token context window excels at efficient reasoning, coding, and creative tasks, making it ideal for developers and organizations seeking fast inference speeds and lower computational costs without sacrificing capability on most standard NLP applications.

This powerful open-source mixture-of-experts model excels at complex reasoning, code generation, and multi-language tasks with a 16K token context window, making it ideal for developers and enterprises seeking cost-effective high-performance inference for demanding applications.

A 7-billion parameter language model with a 32K token context window designed for efficient inference on consumer hardware, ideal for developers and researchers seeking a lightweight alternative to larger models for tasks like text generation, summarization, and code completion without sacrificing quality.

This high-performance mixture-of-experts language model with 16K token context excels at complex reasoning, multi-step problem solving, and handling lengthy documents, making it ideal for developers and enterprises requiring advanced AI capabilities for technical tasks, code generation, and sophisticated content analysis.

This advanced large language model excels at complex reasoning, multi-turn conversations, and processing extensive documents up to 131K tokens, making it ideal for researchers, developers, and enterprises requiring sophisticated natural language understanding for tasks like code generation, analysis, and knowledge-intensive applications.

This lightweight 1.7 billion parameter language model with 33K token context is ideal for developers and researchers seeking efficient inference on resource-constrained devices while maintaining reasonable performance on text generation, summarization, and question-answering tasks.