Moonshot: Kimi K2.5

kimi-k2.5

chatMoonshot

Quick Reference

Input: Text, Image
Output: Text

Context: 262K
Max Output: 16.4K

Input Price: $0.59/M
Output Price: $3.09/M

Author: Moonshot AI
Version: main
Open Source: No

Overview

kimi-k2.5 is Moonshot's most versatile model to date, featuring a native multimodal architecture that simultaneously supports vision and text input, thinking and non-thinking modes, and both conversational and Agent tasks.

Input modalities

TextImage

Output modalities

Text

Capabilities

chatreasoningvision

Features

Function Calling

Structured Output

Caching

Pricing

Per-token prices for Moonshot: Kimi K2.5.

Token Type	Price	Unit
Input	$0.59/M	per million tokens
Output	$3.09/M	per million tokens
Cache Read	$0.06/M	per million tokens

Specifications

Context Window

262Ktokens

Max Input

246Ktokens

Max Output

16.4Ktokens

API Reference

OpenAI-compatible endpoint at https://api.inferoute.ai/v1.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.inferoute.ai/v1",
    api_key=os.environ.get("INFEROUTE_API_KEY"),
)

try:
    response = client.chat.completions.create(
        model="kimi-k2.5",
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Write a haiku about recursion."},
        ],
        max_tokens=512,
        temperature=0.7,
    )

    print(response.choices[0].message.content)
except Exception as e:
    print(f"Error: {e}")