Host AtlasCloud raised DeepSeek V3.1 Terminus output pricing by 5%
Published 28 September 2026
Price move, per 1M tokens
- AtlasCloud · inputunchanged$0.30 → $0.30
- AtlasCloud · output↑ 5%$0.95 → $1.00
- AtlasCloud · cache read↑ 4%$0.130 → $0.135
| host | rate | was | now | change |
|---|---|---|---|---|
| AtlasCloud | input | $0.30 | $0.30 | — |
| AtlasCloud | output | $0.95 | $1.00 | ↑ 5% |
| AtlasCloud | cache read | $0.130 | $0.135 | ↑ 4% |
output: ↑ 5%
If you buy
budget for a slightly higher output cost on your next top-up here, and re-check your cache-read assumptions if your workload leans on cached prompts.
The model
DeepSeek V3.1 Terminusopen the model →
Open weights684.5B parameters164K context5 hosts
intelligence84th of 168 writing62nd of 168 coding100th of 168
DeepSeek V3.1 Terminus is a large downloadable text model with a permissive MIT licence and 37 billion active parameters per token. It scores highest on coding among its measured variants and offers wide provider choice, though it handles text only.
Source
Read on openrouter.ai · we published this on 28 September 2026.
read the original at openrouter.ai ↗