Hy3 preview: pricing, context and benchmarks

What you need to know about Hy3 preview

Tencent, based in China, put Hy3 preview online on April 22, 2026. It accepts text as input and produces text. Its context window reaches 262,144 tokens, larger than 58 % of the models in the registry, and it can write up to 235,929 tokens in one go.

It has been available for about 6 months, long enough for its prices and scores to have settled.

Hy3 preview pricing

On OpenRouter, Hy3 preview costs $0.18 per million input tokens and $0.6 per million output tokens. Counting three tokens read for every token written, its average price is $0.285 per million, more expensive than 28 % of paid models (2.7 times cheaper than the median of $0.76).

A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0007. At 1,000 tasks a day, budget $20 a month. The price calculator redoes this with your own volumes.

Tokens already sent and cached are billed at $0.06 per million.

Performance and benchmarks

Epoch AI does not yet publish a capabilities index for Hy3 preview. We therefore show no made-up performance rating: only price, context and features count towards its score.

Features, privacy and local use

• It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
• It is a reasoning model: it "thinks" before answering, which helps on hard tasks but uses more output tokens.

Its weights are open and downloadable from Hugging Face (other licence): you can run it on your own machines without sending your data to a third party. With 298,786,155,776 billion parameters, it needs about 166,959,775,114 GB of memory at 4-bit quantisation. Check with the VRAM calculator. It was downloaded 81,647 times on Hugging Face last month.

Other Tencent models