# Tencent Hy3

25 Hacker News commenters recommended Tencent Hy3 and 11 criticized it, November 2025 to November 2026. It was recommended in 5 of 13 months. It meets the Hacker Approved badge rule.

**Verdict:** Recommended as a cheap, capable open-weights model that punches above its size for coding and writing. Caveats: slow responses, rate limits and errors on OpenRouter.

## Why people recommend it

- Cheap to use for its capability (4 comments): "except for Hy3 , DeepSeek v4 Pro , and MiMo v2.5 Pro (whose API rates are cheap and/or discounted already)" ([source](https://news.ycombinator.com/item?id=49001259)) "it just works for me for most things I tried and it's exceedingly cheap" ([source](https://news.ycombinator.com/item?id=48848149)) "genuinely good enough as daily drivers, given the costs" ([source](https://news.ycombinator.com/item?id=48937822))
- Strong and surprisingly good overall (4 comments): "Hy3 was a very strong and underrated model." ([source](https://news.ycombinator.com/item?id=49498240)) "was surprised with how good it was" ([source](https://news.ycombinator.com/item?id=49493279)) "Hy3 have all been amazing models." ([source](https://news.ycombinator.com/item?id=48570151))
- Strong coding and benchmark results (3 comments): "Hy3's coding benchmarks hold their own against DeepSeek v4 Pro & MiMo v2.5 Pro" ([source](https://news.ycombinator.com/item?id=48848653)) "I was also surprised to see how (relatively) good it is on coding tasks too." ([source](https://news.ycombinator.com/item?id=49495030)) "the benchmarks are on par with Pro (or above in some cases)" ([source](https://news.ycombinator.com/item?id=48850520))
- Small for how capable it is (2 comments): "Which is impressive as it's smaller and cheaper than the others." ([source](https://news.ycombinator.com/item?id=48858404)) "This model is shockingly small for how capable it is." ([source](https://news.ycombinator.com/item?id=48848190))

## What people warn about

- Slow and error-prone on OpenRouter (2 comments): "My one concern over Hy3 was speed." ([source](https://news.ycombinator.com/item?id=49493072)) "It is really slow on openrouter and I ran into many http errors." ([source](https://news.ycombinator.com/item?id=48850555))
- Rate limits on the free tier (2 comments): "free with generous limits and high availability, until it wasn't" ([source](https://news.ycombinator.com/item?id=48854687)) "I was getting rate limited like crazy" ([source](https://news.ycombinator.com/item?id=48848866))
- Trails rival models in some tests (3 comments): "The Hy3 preview has been a mediocre performer in my benchmarks of security auditing with models" ([source](https://news.ycombinator.com/item?id=48849896)) "I don't see a reason where you would use this model over competitors." ([source](https://news.ycombinator.com/item?id=48848715)) "Worse than GLM-5.2, much more expensive than deepseek v4." ([source](https://news.ycombinator.com/item?id=48857664))

## Alternatives hackers recommend

- [Qwen 3.8 27B](https://hackerapproved.com/p/qwen-3-8-27b.md): 1173 recommend
- [Z.ai GLM](https://hackerapproved.com/p/glm-5-2.md): 1043 recommend
- [Kimi](https://hackerapproved.com/p/kimi-k3.md): 931 recommend
- [Gemma 4](https://hackerapproved.com/p/gemma-4.md): 713 recommend
- [Qwen](https://hackerapproved.com/p/qwen.md): 474 recommend

## Cite as

Hacker Approved, "Tencent Hy3", https://hackerapproved.com/p/hy3/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).