tencent/hy-mt2-1.8b vs tencent/hy3
For 100,000 calls of 2,000 in and 500 out, tencent/hy-mt2-1.8b is cheaper: $17.65 a month at OpenRouter, against $52.80 for tencent/hy3 at OpenRouter — 3.0× the cost.
Cheapest on each
tencent/hy-mt2-1.8b
$17.65/mo
cheapest, at OpenRouter — $0.044 in, $0.177 out per million
tencent/hy3
$52.80/mo
cheapest, at OpenRouter — $0.132 in, $0.528 out per million
Aligned facts
Same rows on both sides, including the ones we cannot fill.
| Attribute | tencent/hy-mt2-1.8b | tencent/hy3 |
|---|---|---|
| Context window | 8K | 262K |
| Accepts | Aa | Aa |
| Sellers | 1 | 2 |
| Cheapest input rate | $0.044 / M | $0.132 / M |
| Cached input rate | ○ no answer | $0.033 / M |
No quality or benchmark row appears here. We hold no throughput or accuracy measurement for either model, and a cost-per-quality figure built from a lab’s own claim would look authoritative and mean nothing.
Cost for this workload — both models, every seller
100,000 calls a month · 2,000 input and 500 output tokens each. Sellers of both models lead, cheapest combined cost first.
| Seller | tencent/hy-mt2-1.8b /mo | tencent/hy3 /mo |
|---|---|---|
| OpenRouter | $17.652026-10-27 | $52.802026-10-27 |
| Novita AI | ○ no answer | $57.002026-10-22 |
Cheapest tier per seller, this workload only. In and output rates, and a cached prefix, are broken out in the cost calculator.