Nex AGI Nex-N2.5-Mini vs OpenAI gpt-oss-20b
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-20b is 1.2× cheaper at a typical mix of 3 input tokens per output token.
- Nex-N2.5-Mini accepts longer prompts: 262K vs 131K tokens.
- gpt-oss-20b's best provider was more reliable over 24 h: 100% vs 98.8%.
- Nex-N2.5-Mini is the newer model (released 2026-09-08).
| Nex-N2.5-Mini | gpt-oss-20b | |
|---|---|---|
| Vendor | Nex AGI | OpenAI |
| Released | 2026-09-08 | 2025-08-05 |
| Input / 1M | $0.025 | $0.018 |
| Output / 1M | $0.10 | $0.09 |
| Cached input / 1M | $0.0025 | $0.0090 |
| Blended / 1M (3:1) | $0.044 | $0.036 |
| Context | 262K | 131K |
| Max output | 236K | 33K |
| Accepts | text, image | text |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 1 | 11 |
| Cheapest provider, output | $0.10 | $0.09 |
| Best provider uptime, 24 h | 98.8% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | — | Operational |
Cost calculator
Nex-N2.5-Mini
$3.00 per month$0.10 per day
gpt-oss-20b
$2.43 per month$0.08 per day
gpt-oss-20b saves $0.57 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Nex-N2.5-Mini with