Host Sail Research repriced Kimi K3: input down 30%, cache read up 23%
Published 22 September 2026
Price move, per 1M tokens
- Sail Research · input↓ 30%$2.14 → $1.50
- Sail Research · outputunchanged$10.76 → $10.76
- Sail Research · cache read↑ 23%$0.244 → $0.300
| host | rate | was | now | change |
|---|---|---|---|---|
| Sail Research | input | $2.14 | $1.50 | ↓ 30% |
| Sail Research | output | $10.76 | $10.76 | — |
| Sail Research | cache read | $0.244 | $0.300 | ↑ 23% |
input: ↓ 30%cache read: ↑ 23%
If you buy
Prompt-heavy work at Sail Research now costs less, while repeated context reads cost more, so re-check your cache hit rate 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 22 September 2026.
read the original at openrouter.ai ↗