OpenAI gpt-oss-safeguard-20b vs Tencent Hy3
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
- gpt-oss-safeguard-20b is 1.8× cheaper at a typical mix of 3 input tokens per output token.
- Hy3 accepts longer prompts: 262K vs 131K tokens.
- Hy3 is the newer model (released 2026-07-06).
| gpt-oss-safeguard-20b | Hy3 | |
|---|---|---|
| Vendor | OpenAI | Tencent |
| Released | 2025-10-29 | 2026-07-06 |
| Input / 1M | $0.075 | $0.132 |
| Output / 1M | $0.30 | $0.528 |
| Cached input / 1M | $0.037 | $0.033 |
| Blended / 1M (3:1) | $0.131 | $0.231 |
| Context | 131K | 262K |
| Max output | 66K | 128K |
| Accepts | text | text |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 1 | 5 |
| Cheapest provider, output | $0.30 | $0.528 |
| Best provider uptime, 24 h | 99.93% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | — |
Cost calculator
gpt-oss-safeguard-20b
$9.00 per month$0.30 per day
Hy3
$15.84 per month$0.53 per day
gpt-oss-safeguard-20b saves $6.84 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare gpt-oss-safeguard-20b with