Tencent says Hy4 flash handled more than 50 trillion tokens on its first day

In a November 18, 2026 update, Tencent’s Hunyuan team said its Hy4 flash model handled more than 50 trillion tokens on its first day of availability—a first-day record for the Hunyuan model series. Tencent also said the model topped the daily large-language-model ranking on OpenRouter that day. These usage and ranking figures are Tencent’s claims.

On Tencent’s WorkBuddy platform, first-day usage was 10 times that of Hy4 preview on its first day, with Hy4 flash completing more than 50 million tasks, according to the company. Tencent said the model generates about 200 tokens per second and processed more than 1 billion tokens per second at peak.

Released on November 16, Hy4 flash has 224 billion total parameters, including 64 billion Engram parameters, and 12 billion active parameters. It supports multimodal input and a context length of 1 million tokens. Tencent listed prices of 0.5 yuan per million input tokens, 2 yuan per million output tokens and 0.02 yuan when a cache is hit—substantially lower than Hy4’s pricing.

The Hunyuan team said Hy4 flash performed slightly better overall than the larger Hy4 preview while costing less. On Tencent’s internal WorkIndex evaluation, which covers tasks including presentations, document editing, spreadsheet repair, audio and video processing, and visual understanding, its per-task cost was one-thirteenth that of Hy4 preview and one-twentieth that of Hy4, according to the team.