T
Hy3 previewOPEN
Hy3 preview (Tencent): live API pricing, context window and the best open-source alternatives, tracked daily by olud.ai.
Prices update automatically — checked hourly against provider list prices.
Benchmarks & performance
Independent benchmark scores for Hy3 preview, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.
For the same budget, Hy3 preview delivers 51 times more capability. Open weights also mean you can self-host it and pay nothing per token.
About this model
Hy3 preview is an open-weight AI model by Tencent. You can download and self-host it for free; the prices below are hosted-API list prices, tracked hourly, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Hy3 preview?
Hy3 preview is an AI language model from Tencent. It is open-weight: you can download it and run it on your own hardware, for free. It scores 33.6 on the Artificial Analysis intelligence index.
Is Hy3 preview free?
The weights are free and open — you can self-host Hy3 preview and pay nothing per token. If you prefer a hosted API, list prices are $0.06 per million input tokens and $0.21 per million output tokens.
What is Hy3 preview good at?
Independent benchmarks from Artificial Analysis give it GPQA 86.7%, Humanity's Last Exam 25.5%, Long Context Reasoning 54.7%, SciCode 41.2%, IFBench 63.1%, τ²-Bench 92.7%, Terminal-Bench Hard 34.1%.
How fast is Hy3 preview?
It generates about 163 tokens per second, with a median 1.8s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Hy3 preview?
Yes. Hy3 preview has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.