Host Mancer 2 cut gpt-oss-120b output pricing by 20%
Published 16 September 2026
Price move, per 1M tokens
- Mancer 2 · input↓ 9%$0.055 → $0.050
- Mancer 2 · output↓ 20%$0.50 → $0.40
| host | rate | was | now | change |
|---|---|---|---|---|
| Mancer 2 | input | $0.055 | $0.050 | ↓ 9% |
| Mancer 2 | output | $0.50 | $0.40 | ↓ 20% |
output: ↓ 20%
If you buy
output-heavy workloads on this host now stretch further per top-up, so re-check your spend split between input and output before your next refill.
The model
gpt-oss-120bopen the model →
Open weights120.4B parameters131K context26 hosts
intelligence122nd of 168 writing138th of 168 coding126th of 168
gpt-oss-120b is a downloadable text model you can run yourself, because only a fraction of its parameters work on each token. Its licence allows commercial use, changes and redistribution, and its measured quality sits mid-field to lower-field on the preference boards.
Source
Read on openrouter.ai · we published this on 16 September 2026.
read the original at openrouter.ai ↗