Submit
Moonshot AIWeights not listed·1049K context·— params

Kimi K2.8 Previewmoonshot/kimi-k2-8-preview

Kimi K2.8 Preview is available in Kimi Code for coding and agent workflows, with image and video input, a 1,048,576-token context and low, high or max reasoning effort. The existing kimi-for-coding ID now selects this preview.

Availability and billing notes

Reviewed September 21, 2026 · check the linked provider documentation for later changes.

Access uses eligible Kimi Code membership plans: the current documentation lists Plus and above for new plans and Andante and above for legacy plans. Go has no coding quota.

No standalone pay-as-you-go token price or downloadable K2.8 weights were verified. Subscription quota is not converted into an invented per-token price.

Official source 1 →Official source 2 →

Pricing across providers

No current verified API pricing is listed. See the official model documentation for availability and billing.

Capabilities

  • code
  • reasoning
  • vision
  • agent

Technical specs

Context
1049K
Max output
—
Parameters
—
Release
2026-09-11
Training cutoff
—
License
—
Official documentation →

Similar models

Compare with

  • Kimi K2.8 Preview vs DeepSeek V4.1 Flash
    Comparison planned — not yet published
  • Kimi K2.8 Preview vs GLM 5.3 Flash
    Comparison planned — not yet published
  • Kimi K2.8 Preview vs Kimi K2.5
    Comparison planned — not yet published

Frequently asked

How much does Kimi K2.8 Preview cost?+
No current verified API pricing is listed. This does not mean the model is free or that a hosted API is currently available. Check the official model documentation below.
How do I access Kimi K2.8 Preview from outside China?+
Availability, account verification and payment methods vary by provider and region. Check the official documentation and the selected provider's access requirements before integrating. A directory listing does not guarantee global API access.
Is Kimi K2.8 Preview open-source?+
Downloadable weights are not listed in this directory for Kimi K2.8 Preview. See the official documentation and availability notes for API, subscription or planned weight-release details.
What's the maximum context window for Kimi K2.8 Preview?+
The model supports up to 1,048,576 tokens of context (input + output). Some hosted versions may impose a smaller limit — check the "Context" column in the pricing matrix for each provider.