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
Relays11 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 11 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: 11/08/2026, 08:15.

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.