Digital Event Horizon
Together AI has launched Tencent Hy4, a powerful AI model that introduces Polymorphic Inference, allowing developers to run open models in their existing harnesses. This new feature provides developers with access to a wide range of high-quality, open-source models that can be fine-tuned and adapted to specific use cases. With its ability to accept images alongside text, Tencent Hy4 is a versatile tool for tasks such as image recognition and analysis, and is available on serverless inference with a competitive pricing model.
Tencent Hy4 is a powerful AI model that introduces Polymorphic Inference, allowing developers to run open models in their existing harnesses. The model is available on serverless inference with competitive pricing ($0.83 per 1M input tokens, $2.50 per 1M output tokens, and $0.042 per 1M cached input tokens). Tencent Hy4 can accept both text and image input, making it a versatile tool for a wide range of applications. The model has been trained on a variety of tasks, including professional software, office work, financial research, and game development. The launch of Tencent Hy4 is part of an effort to democratize access to high-quality, open-source models and provide developers with the tools they need to build innovative applications.
Together AI has recently made a significant addition to its platform with the launch of Tencent Hy4, a powerful AI model that introduces Polymorphic Inference, allowing developers to run open models in their existing harnesses. This new feature, which is part of the Together Link, enables developers to access a wide range of high-quality, open-source models that can be fine-tuned and adapted to specific use cases. The model, which has a 1M-token context window and accepts both text and image input, has been trained on a variety of tasks, including professional software, office work, financial research, and game development.
The launch of Tencent Hy4 on Together AI is part of a broader effort to expand the platform's capabilities and provide developers with access to a wide range of high-quality, open-source models. The model is available on serverless inference, with a price of $0.83 per 1M input tokens, $2.50 per 1M output tokens, and $0.042 per 1M cached input tokens. It also supports JSON output and tool calling, making it a versatile tool for a wide range of applications.
One of the key features of Tencent Hy4 is its ability to accept images alongside text, making it a powerful tool for tasks such as image recognition and analysis. The model has also been trained on a variety of professional software, including Blender and CAD tools, making it a useful tool for developers working on complex projects.
In addition to its technical capabilities, the launch of Tencent Hy4 on Together AI is also notable for its potential to democratize access to high-quality, open-source models. By providing developers with access to a wide range of high-quality models, Together AI is helping to level the playing field and enable developers of all levels to build innovative applications.
The launch of Tencent Hy4 on Together AI is part of a broader trend towards the development of more advanced and versatile AI models. As the field of AI continues to evolve, it is likely that we will see the development of even more powerful and sophisticated models that can be used to solve complex problems.
In the near future, developers can expect to see even more advanced models and features on Together AI, including the ability to run open models in their existing harnesses and access a wide range of high-quality, open-source models. With the launch of Tencent Hy4, Together AI is taking a major step forward in its efforts to provide developers with the tools and resources they need to build innovative applications.
Related Information:
https://www.digitaleventhorizon.com/articles/Tencent-Hy4-Revolutionizes-AI-Inference-with-Polymorphic-Inference-and-Serverless-Inference-deh.shtml
https://www.together.ai/blog/tencent-hy4
Published: Thu Nov 19 20:16:30 2026 by llama3.2 3B Q4_K_M