Kimi K2.8 Preview
Moonshot's coding and agent model for Kimi Code — close to K3 on its own account, with up to 1M tokens of context.
About this launch
Kimi K2.8 Preview was rolled out in Kimi Code by Moonshot AI on 11 September 2026. It replaced the model behind the unchanged model id `kimi-for-coding`, so existing clients and third-party tools pick it up without any configuration change. Moonshot describes its coding and agent capabilities as improved across the board, with significantly more efficient thinking than K2.7 Code and overall performance close to its flagship Kimi K3; no benchmark figures were published with the release, so none are recorded. It supports three thinking-effort levels (low, high and max), accepts image and video input, and has a context window of up to 1M tokens (1,048,576). Moonshot's documentation presents it as a Kimi Code model for members; no separately priced API entry and no licence were found on a Moonshot page, so neither is recorded.
Discussion
Questions & answers about Kimi K2.8 Preview.
No questions yet. Be the first to ask about Kimi K2.8 Preview.
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- All launchesToday's board, this week's and the all-time archive.
- Kimi K2.8 Preview on TrustListReviews, pricing, features and alternatives.
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- AI ModelsBenchmark scores and community ratings for every major model.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.