Kimi 2.6

kimi-k2.6

A new Kimi model for long context and agent workflows

Kimi 2.6 targets long-context work, code understanding, complex reasoning, and agent workflows. It is suitable for cross-file analysis, knowledge-intensive Q&A, tool use, and high-quality Chinese-language tasks.

262K context262K context

Released2026-04

Relays28 sites

Long-context analysisAgent workflowsCode understandingStrong Chinese performance

Model information

Model ID: kimi-k2.6
Context: 262.1K
Max input: -
Max output: 262.1K
Knowledge cutoff: 2025-01
Open weights: Supported
License: -
Release date: 2026-04

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: SupportedTemperature: Supported

Moonshot AI Official Pricing

CNY

Updated: 2026-04-01T00:00:00.000+08:00Source

Input

¥6.5/ 1M tokens

Output

¥27/ 1M tokens

Cache read

¥1.1/ 1M tokens

Relay Comparison

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

Unit: token prices are ¥ / 1M tokens; per-request and per-second rows use their shown unit

9527code

https://9527.codesToken billing

Price range ¥0.65 - ¥3.9 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
free	Token	¥0.65	¥2.7	¥0.11	-
国产官方模型	Token	¥3.9	¥16.2	¥0.66	-

CUN.ai

cun.aiToken billing

Price range ¥0.65 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
hvoy	Token	¥0.65	¥2.7	¥0.0975	-

天天中转站

https://apitiantian.comToken billing

Price range ¥1.27 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
国模2折福利	Token	¥1.27	¥5.36	¥0.21	¥0
国模福利-chat端点	Token	¥1.27	¥5.36	¥0.21	¥0
国模福利-messages端点	Token	¥1.27	¥5.36	¥0.21	¥0

8sToken

8stoken.comToken billing

Price range ¥3.25 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
国产模型聚合专区	Token	¥3.25	¥13.5	¥0.55	¥3.25

Modelsell

modelsell.comToken billing

Price range ¥6.46 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
Alibaba	Token	¥6.46	¥27.2	¥1.09	-
official	Token	¥6.46	¥27.2	¥1.09	-

PackyCode

packyapi.aiToken billing

Price range ¥6.17 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
kimi-officially	Token	¥6.17	¥25.65	¥1.04	-

RunAPI

https://runapi.hostToken billing

Price range ¥3.25 - ¥5.07 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
kimi-sale	Token	¥3.25	¥13.5	¥0.6501	-
default	Token	¥5.07	¥21.06	¥1.01	-

sidrune

https://sidrune.ai/Token billing

Price range ¥3.9 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
Kimi-余额	Token	¥3.9	¥16.2	¥0.66	¥3.9

Tokenflyapi

api.tokenflyapi.comToken billing

Price range ¥13.2 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
国产模型	Token	¥13.2	¥54.81	-	¥2.23

远桥云 API

yuanqiaoyun.comToken billing

Price range ¥5.2 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
kimi	Token	¥5.2	¥21.6	¥0.88	-

How should Kimi 2.6 relay pricing be compared?

This Kimi 2.6 pricing page compares official pricing with public prices from 28 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: 10/11/2026, 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.