Host Reka cut Qwen3.8 27B output pricing by 2%
Published 21 September 2026
Price move, per 1M tokens
- Reka · inputunchanged$0.20 → $0.20
- Reka · output↓ 2%$2.55 → $2.50
- Reka · cache read↓ 41%$0.085 → $0.050
| host | rate | was | now | change |
|---|---|---|---|---|
| Reka | input | $0.20 | $0.20 | — |
| Reka | output | $2.55 | $2.50 | ↓ 2% |
| Reka | cache read | $0.085 | $0.050 | ↓ 41% |
output: ↓ 2%
If you buy
Output costs a little less and cached reads much less, so long, repetitive prompts now suit this host better; re-check your cache hit rate before your next top-up.
The model
Qwen3.8 27Bopen the model →
Open weights27.8B parameters262K context20 hosts
intelligence63rd of 168 writing93rd of 168 coding45th of 168 agents33rd of 55
Qwen3.8 27B is a downloadable model you can run yourself, and its measured strength is maths and reasoning. Agentic recovery and tool use sit near the bottom of the field, so it suits a solver rather than an agent that has to get itself back on track.
Source
Read from the hosts' own published rates · we published this on 21 September 2026.