Hy4 flash by Tencent added to BenchGecko
Tencent's cheapest Hy model · 224B total and 12B active parameters · 1M token context · $0.070 input and $0.281 output per million tokens.
What was added
Hy4 flash by Tencent is now listed on BenchGecko. Tencent released it on November 16, 2026 as its most cost effective Hy model to date, twelve days after the flagship Hy4. The API model id on Tencent Cloud TokenHub is hy4-flash.
Size and context
Tencent describes Hy4 flash as a model with 224B total parameters, including 64B Engram parameters, and 12B active parameters per token. Like Hy4 it is natively multimodal with a 1M token context window, taking text and images as input and returning text. Tencent says it plans to release Hy4 flash as an open weight model, so BenchGecko lists it as proprietary for now.
Pricing
Tencent lists Hy4 flash at $0.070 per million input tokens, $0.281 per million output tokens and $0.003 per million cached input tokens. Hy4 is listed by Tencent at $0.834 input, $2.501 output and $0.042 cached input, so Hy4 flash costs about 8% of Hy4 on input and about 11% on output. Through November 30, Tencent Cloud TokenHub applies 50% off API pricing and WorkBuddy users get it for free. BenchGecko shows the list price. Tencent says Hy4 flash will launch on OpenRouter soon.
BenchGecko has also set the Hy4 row back to Tencent's list price of $0.834 input and $2.501 output, which the Hy4 flash announcement restates.
Benchmarks
Tencent reports a blind evaluation with 85 internal WorkBuddy users across 259 tasks in 27 categories, where Hy4 flash reached user satisfaction close to Claude Haiku 5.5 with the shortest end to end completion time. That is a vendor evaluation. BenchGecko has no independent scores yet and will add them to the model page as they arrive.
Source: BenchGecko
Written automatically from BenchGecko's tracked data for this period; every number comes from the changelog, model, mindshare and pricing datasets. Checked against the source data before publishing.