Text-embedding-3 series models are the latest and most capable embedding model from OpenAI.

Text-embedding-3 series models are the latest and most capable embedding model from OpenAI.

Focused on advanced reasoning and solving complex problems, including math and science tasks. Ideal for applications that require deep contextual understanding and agentic workflows.

Focused on advanced reasoning and solving complex problems, including math and science tasks. Ideal for applications that require deep contextual understanding and agentic workflows.

o3-mini includes the o1 features with significant cost-efficiencies for scenarios requiring high performance.

Excels in image reasoning capabilities on high-res images for visual understanding apps.

Llama 3.3 70B Instruct offers enhanced reasoning, math, and instruction following with performance comparable to Llama 3.1 405B.

Advanced image reasoning capabilities for visual understanding agentic apps.

Llama 4 Maverick 17B 128E Instruct FP8 is great at precise image understanding and creative writing, offering high quality at a lower price compared to Llama 3.3 70B

The Llama 3.1 instruction tuned text only models are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.

Enhanced Mistral Small 3 with multimodal capabilities and a 128k context length.

3.8B parameters Small Language Model outperforming larger models in reasoning, math, coding, and function-calling

First small multimodal model to have 3 modality inputs (text, audio, image), excelling in quality and efficiency

Llama 4 Scout 17B 16E Instruct is great at multi-document summarization, parsing extensive user activity for personalized tasks, and reasoning over vast codebases.

Codestral 25.01 by Mistral AI is designed for code generation, supporting 80+ programming languages, and optimized for tasks like code completion and fill-in-the-middle

The Llama 3.1 instruction tuned text only models are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.

Ministral 3B is a state-of-the-art Small Language Model (SLM) optimized for edge computing and on-device applications. As it is designed for low-latency and compute-efficient inference, it it also the perfect model for standard GenAI applications that have

Mistral Medium 3 is an advanced Large Language Model (LLM) with state-of-the-art reasoning, knowledge, coding and vision capabilities.

Phi-4 14B, a highly capable model for low latency scenarios.

Lightweight math reasoning model optimized for multi-step problem solving