Host AtlasCloud cut DeepSeek V3.2 Exp output pricing by 51%
Published 28 September 2026
Price move, per 1M tokens
- AtlasCloud · input↓ 50%$0.270 → $0.134
- AtlasCloud · output↓ 51%$0.41 → $0.20
- AtlasCloud · cache read↓ 75%$0.270 → $0.067
| host | rate | was | now | change |
|---|---|---|---|---|
| AtlasCloud | input | $0.270 | $0.134 | ↓ 50% |
| AtlasCloud | output | $0.41 | $0.20 | ↓ 51% |
| AtlasCloud | cache read | $0.270 | $0.067 | ↓ 75% |
output: ↓ 51%
If you buy
Output and cache reads now cost far less, so long generations and heavy context reuse are easier to justify; re-check your cache-hit assumptions and budget.
The model
DeepSeek V3.2 Expopen the model →
Open weights685.4B parameters164K context3 hosts
intelligence78th of 168 writing55th of 168 coding77th of 168
Source
Read on openrouter.ai · we published this on 28 September 2026.
read the original at openrouter.ai ↗