Moonshot AI

Kimi K2.8 Preview

kimi-k2.8-preview

A coding model with efficient thinking and up to 1M context, available through Kimi Code.

Kimi K2.8 Preview is a Kimi Code programming model. The API id is kimi-for-coding. It is available on Andante / Plus and above, with up to a 1M context window and thinking levels low, high, and max (verified 2026-10-20).

1M context1M context
Released2026-09-11
Relays6 sites
code generationreasoninglong context

Model information

Model ID
kimi-k2.8-preview
Context
1M
Max input
-
Max output
-
Knowledge cutoff
-
Open weights
Not supported
License
-
Release date
2026-09-11

Input

Text: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported

Output

Text: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported

API capabilities

Reasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported

Relay Comparison

Compare token, per-request, or per-second pricing by relay channel.

How should Kimi K2.8 Preview relay pricing be compared?

This Kimi K2.8 Preview pricing page compares official pricing with public prices from 6 listed AI gateways. Token prices are shown in CNY per 1M tokens, while per-request, per-second, and per-character rows use the unit shown in the table. Last updated: 10/25/2026, 23:15.

Data sources
Public price catalogs, official pricing records, and monitoring results.
Metric definitions
Uptime means successful probe response rate, fake-rate signals possible model mismatch or abnormal output risk, and latency is average API response time.
Risk note
Relay gateways are third-party services. Pricing, billing, privacy, and stability can change; start with a small top-up and verify reliability before continued use.