Host Relace cut Kimi K3 input pricing by 12%
Published 16 September 2026
Price move, per 1M tokens
- Relace · input↓ 12%$2.40 → $2.10
- Relace · output↓ 9%$12.00 → $10.95
- Relace · cache read↓ 4%$0.24 → $0.23
| host | rate | was | now | change |
|---|---|---|---|---|
| Relace | input | $2.40 | $2.10 | ↓ 12% |
| Relace | output | $12.00 | $10.95 | ↓ 9% |
| Relace | cache read | $0.24 | $0.23 | ↓ 4% |
input: ↓ 12%
If you buy
anyone running long prompts through this model here now gets more room per top-up, so re-check your cache and output settings before your next billing cycle.
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 16 September 2026.
read the original at openrouter.ai ↗