OpenAI gpt-oss-120b vs Tencent Hy3 preview
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Both cost about the same at a typical 3:1 input/output mix.
- Hy3 preview accepts longer prompts: 262K vs 131K tokens.
- gpt-oss-120b output costs $0.15 per 1M via Near AI, against the list price of $0.60.
- gpt-oss-120b's best provider was more reliable over 24 h: 100% vs 99.44%.
- Hy3 preview is the newer model (released 2026-04-22).
| gpt-oss-120b | Hy3 preview | |
|---|---|---|
| Vendor | OpenAI | Tencent |
| Released | 2025-08-05 | 2026-04-22 |
| Input / 1M | $0.15 | $0.18 |
| Output / 1M | $0.60 | $0.60 |
| Cached input / 1M | $0.075 | $0.06 |
| Blended / 1M (3:1) | $0.262 | $0.285 |
| Context | 131K | 262K |
| Max output | 66K | 236K |
| Accepts | text | text |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 25 | 1 |
| Cheapest provider, output | $0.15 | $0.60 |
| Best provider uptime, 24 h | 100% | 99.44% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | — |
Cost calculator
gpt-oss-120b
$18.00 per month$0.60 per day
Hy3 preview
$19.80 per month$0.66 per day
gpt-oss-120b saves $1.80 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare gpt-oss-120b with