TxGemma API is a collection of open-source machine learning models designed to generate predictions, classifications, or text based on therapeutic-related data.
Model Type: LLm
Qwen2.5-Omni-7B API
The Qwen2.5-Omni-7B API provides developers with OpenAI-compatible methods to interact with the model, enabling the processing of text, image, audio, and video inputs, and generating both text and natural speech responses in real-time.
Model Type: Chat
Ideogram 3.0 API
Ideogram 3.0 API emerges as a significant milestone in text-to-image generation technology. Developed by Ideogram AI, this advanced model transforms textual descriptions into high-quality, visually appealing images, catering to diverse applications across multiple industries.
Model Type: Image Generation
Qwen2.5-VL-32B API
Qwen2.5-VL-32B API has garnered attention for its outstanding performance in various complex tasks, combining both image and text data for an enriched understanding of the world. Developed by Alibaba, this 32 billion parameter model is an upgrade of the earlier Qwen2.5-VL series, pushing the boundaries of AI-driven reasoning and visual comprehension.
Model Type: LLm
Veo 2 API
The Veo 2 API is a powerful interface that enables developers to integrate AI-driven video generation into applications, allowing for the creation of high-quality, realistic videos from textual descriptions with customizable cinematic controls and real-time rendering capabilities.
Model Type: Video
Wan 2.1 API
Wan 2.1 API is an advanced AI-driven video generation interface that transforms text or image inputs into high-quality, realistic videos using state-of-the-art deep learning models.
Model Type: Video
Sora API
The Sora API is a powerful AI-driven tool that enables seamless text-to-video generation, allowing developers to create high-quality, realistic videos through an intuitive and scalable interface.
Model Type: Video
O3 Mini API
The O3 Mini API is a lightweight, high-efficiency AI interface designed for real-time natural language processing and multimodal interactions, optimized for low-latency and resource-constrained environments.
Model Type: Chat
Gemma 3 27B API
The Gemma 3 27B API is a multimodal AI model developed by Google, featuring 27 billion parameters, capable of processing text, images, and short videos, supporting over 140 languages, and handling context windows up to 128,000 tokens, designed to run efficiently on a single GPU.
Model Type: Chat
Gemini 2.0 Flash API
The Gemini 2.0 Flash API is a highly efficient, scalable interface that empowers developers with advanced multi-modal processing, rapid response times, and robust integration capabilities for a diverse range of applications.
Model Type: Chat