Kimi K3 repriced across 3 hosts, from an 8% rise at Relace (all rates) to a 20% cut at Wafer (input and cache read)
Published 24 September 2026
Price move, per 1M tokens
- Wafer · input↓ 20%$2.49 → $1.99
- Wafer · outputunchanged$14.50 → $14.50
- Wafer · cache read↓ 20%$0.25 → $0.20
- Sail Research · input↓ 10%$1.50 → $1.35
- Sail Research · output↑ 7%$10.76 → $11.50
- Sail Research · cache readunchanged$0.30 → $0.30
- Relace · input↑ 8%$1.95 → $2.10
- Relace · output↑ 8%$9.75 → $10.50
- Relace · cache read↑ 8%$0.195 → $0.210
| host | rate | was | now | change |
|---|---|---|---|---|
| Wafer | input | $2.49 | $1.99 | ↓ 20% |
| Wafer | output | $14.50 | $14.50 | — |
| Wafer | cache read | $0.25 | $0.20 | ↓ 20% |
| Sail Research | input | $1.50 | $1.35 | ↓ 10% |
| Sail Research | output | $10.76 | $11.50 | ↑ 7% |
| Sail Research | cache read | $0.30 | $0.30 | — |
| Relace | input | $1.95 | $2.10 | ↑ 8% |
| Relace | output | $9.75 | $10.50 | ↑ 8% |
| Relace | cache read | $0.195 | $0.210 | ↑ 8% |
Wafer input and cache read: ↓ 20%Sail Research input: ↓ 10%Sail Research output: ↑ 7%Relace all rates: ↑ 8%
If you buy
Relace now costs more to run for both input and output, so check whether your workload still fits the budget you set before your next top-up.
The model
Kimi K3open the model →
Open weights2779.9B parameters1049K context25 hosts
intelligence12th of 168 writing18th of 168 coding6th of 168 agents10th of 55
Kimi K3 is Moonshot AI's massive-scale mixture-of-experts model with 2.8 trillion total parameters and 104 billion active per word. It excels at reasoning and web-development tasks, and handles up to one million tokens in a single request, though its weights carry commercial restrictions.
Source
Read on openrouter.ai · we published this on 24 September 2026.
read the original at openrouter.ai ↗