Kimi K2.5

kimi-k2.5

An earlier Kimi frontier model for long-context agents, coding, and multimodal work

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

262K context262K context

Released2026-01

Relays17 sites

long contextcode generationmultimodalreasoning

Model information

Model ID: kimi-k2.5
Context: 262.1K
Max input: -
Max output: 262.1K
Knowledge cutoff: 2025-01
Open weights: Supported
License: -
Release date: 2026-01

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.

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

OmniaKey

omniakey.comToken billing

Price range ¥1.2 / 1M tokens

Cache write¥0.2

Channel	Billing	Input	Output	Cache hit	Cache write
default	Token	¥1.2	¥6	¥0.2	¥0.2

8sToken

8stoken.comToken billing

Price range ¥2 / 1M tokens

国产模型聚合专区

Cache hit¥0.35

Channel	Billing	Input	Output	Cache hit	Cache write
国产模型聚合专区	Token	¥2	¥10.5	¥0.35	¥2

PackyCode

packyapi.aiToken billing

Price range ¥2 / 1M tokens

Cache hit¥0.35

Channel	Billing	Input	Output	Cache hit	Cache write
bailian	Token	¥2	¥10.5	¥0.35	-

CUN.ai

cun.aiToken billing

Price range ¥0.4 / 1M tokens

Cache hit¥0.04

Channel	Billing	Input	Output	Cache hit	Cache write
hvoy	Token	¥0.4	¥2.1	¥0.04	-

LinoRoute

linoroute.comToken billing

Price range ¥0.6 - ¥0.9 / 1M tokens

Self-Deployed-2

Self-Deployed-3

Channel	Billing	Input	Output	Cache hit	Cache write
Self-Deployed-2	Token	¥0.6	¥3.15	-	-
Kimi-1	Token	¥0.9	¥4.72	-	-
Self-Deployed-3	Token	¥0.9	¥4.72	-	-

ClaudeCN

claudecn.topToken billing

Price range ¥0.54 / 1M tokens

Cache hit¥0.09

Channel	Billing	Input	Output	Cache hit	Cache write
国产模型	Token	¥0.54	¥2.7	¥0.09	-

RunAPI

https://runapi.hostToken billing

Price range ¥2 - ¥3.12 / 1M tokens

Cache hit¥0.624

Channel	Billing	Input	Output	Cache hit	Cache write
kimi-sale	Token	¥2	¥10.5	¥0.4	-
default	Token	¥3.12	¥16.38	¥0.624	-

AIGC Token

aigc-token.comToken billing

Price range ¥4 - ¥16 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
AzurePlus	Token	¥4	¥21	¥0.8	-
default	Token	¥4	¥21	¥0.8	-
AzurePro	Token	¥16	¥84	¥3.2	-

niccom

niccom.com.cnToken billing

Price range ¥0.76 / 1M tokens

Cache hit¥0.14

Cache hit¥0.14

Channel	Billing	Input	Output	Cache hit	Cache write
default	Token	¥0.76	¥3.96	¥0.14	-
官转分组	Token	¥0.76	¥3.96	¥0.14	-

UniLink

api.unilink.workToken billing

Price range ¥2.4 / 1M tokens

Cache hit¥0.42

Channel	Billing	Input	Output	Cache hit	Cache write
国产模型	Token	¥2.4	¥12.6	¥0.42	-

How should Kimi K2.5 relay pricing be compared?

This Kimi K2.5 pricing page compares official pricing with public prices from 17 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: 10/23/2026, 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.