Summary
A notice was added regarding the new support for kimi-k3.1-pro and kimi-k3 within Batch API, which outlines the price and applicable scope, corresponding to the release of the new model.
LLM generationLLM The summary is machine-generated; please refer to the original text for important information.
Permanent link
https://daily.maas.click/item/obs_d5e381c53e563803d56bb3ce436622aae6f66164d0c2e7e328b6dd613b5fc19f/Source page
https://platform.kimi.com/docs/changelog ↗This link points to the source's official page (not content on this site).
changesExcerpt
The following is an excerpt of the saved changes
Evidence level: source discrepancy (source_diff) — this is a change to the crawled source page; changes in the pricing page text do not represent verified price adjustments.
1 lines added
- 📦 Batch API 支持 Kimi K3.1 Pro 与 Kimi K3Batch API 批量推理新增支持 kimi-k3.1-pro 和 kimi-k3 模型（此前仅支持 kimi-k2.7-code 与 kimi-k2.6），国内外同步上线。批量推理价格仍为标准价格的 60%；其中 kimi-k3.1-pro、kimi-k3 的批量任务同样收取缓存写入（Cache Write）费用，且由于批处理请求为异步并发处理，缓存命中为尽力而为。详见 Batch API 指南 与 批量推理定价。
Revision history (2 versions)
- r1
- r2