moonshotai

Kimi K2.5

Input / 1M: $0.63
Output / 1M: $3.15
Context: 256,000 tokens
Catalog: Gateway catalog

About this model

kimi-k2.5 is Kimi's most versatile model to date, featuring a native multimodal architecture that supports both visual and text input, thinking and non-thinking modes, and dialogue and agent tasks.

Replaces Kimi K2 Instruct: input $0.5985 → $0.63 per 1M (+5%), output $2.415 → $3.15 per 1M (+30%), context 131K → 256K, max output 131K → 256K.

text inputimage inputtext outputlanguage

Use with MiniRouter Compare this model View docs

Use an endpoint supported by this model.

Get a key for this setup →

1const response = await fetch('https://api.minirouter.sh/v1/chat/completions', {2  method: 'POST',3  headers: {4    Authorization: `Bearer ${process.env.MINIROUTER_KEY}`,5    'Content-Type': 'application/json',6  },7  body: JSON.stringify({8    model: 'moonshotai/kimi-k2.5',9    messages: [{ role: 'user', content: 'Why is the sky blue?' }],10    max_tokens: 1024,11  }),12})13 14const data = await response.json()15console.log(data.choices[0].message.content)

Read docs →

Overview

Model type: language
Context window: 256,000
Maximum output: 256,000
Input / 1M tokens: $0.63
Output / 1M tokens: $3.15
Released: 2026-01-26

Prices include the MiniRouter fee. Compatibility snapshot: 2026-08-06. Input: text, image. Output: text.

Endpoints

/v1/chat/completions/v1/messages/v1/responses

Platform-funded routing only. Caller BYOK credentials and OIDC-based upstream authentication are intentionally excluded; authenticate with a MiniRouter bearer key.

Captured parameters: max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning.

Structured output: Not enforced; a requested format is dropped and the answer is plain text. How it works

API

Use the setup panel above to switch between Chat Completions, Messages, and client configurations. Every snippet keeps the model ID unchanged.

Base URLhttps://api.minirouter.sh/v1

Model IDmoonshotai/kimi-k2.5

Providers

MiniRouter selects from the configured routes below. Priority is the catalog order, not a latency or availability score.

Provider	Priority	Input / 1M	Output / 1M	Parameters	Access
vercel	1	$0.63	$3.15	max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning	MiniRouter balance