kimi-k2.5

completions

byopenrouter

kimi-k2.5

completions

Published by: moonshotaiProvider:

openrouter

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.

Released

Jan 27, 2026

Knowledge

Jul 31, 2025

License

MIT

Context

262144

Input

$0.38 / 1M tokens

Output

$2.48 / 1M tokens

Cached

$0.15 / 1M tokens

Capabilities: tools, reasoning

Accepts: text, image

Returns: text

Released Jan 27, 2026Knowledge Cutoff: Jul 31, 2025License: MIT

Context: 262144 Input: $0.38 / 1M tokensOutput: $2.48 / 1M tokensCached: $0.15 / 1M tokensCapabilities: tools, reasoningAccepts: text, imageReturns: text

Access kimi-k2.5 through LangDB AI Gateway

Recommended

Integrate with moonshotai's kimi-k2.5 and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Benchmark Results for kimi-k2.5

Category Performance Scores:

Science: Score 81.01 (Top 5% - Rank #17)
Writing: Score 71.75 (Top 8% - Rank #27)
Academia: Score 67.22 (Top 3% - Rank #11)
Marketing: Score 71.48 (Top 4% - Rank #14)
Programming: Score 39.50 (Top 6% - Rank #21)

Overall Performance: 66.19477777777777 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
HLE	29.40	Top 2%	General Knowledge
GPQA	87.75	Top 3%	STEM (Physics, Chemistry, Biology)
SciCode	49.00	Top 3%	Scientific
MMLU-Pro	87.10	Top 5%	General Knowledge
AA Coding Index	39.50	Top 6%	Programming
AAII	46.70	Top 3%	General

GPQA Score: 87.75 - Graduate-level reasoning benchmark

Model Comparison:

Provider: openrouter

Model Type: completions

Context Size: 262144 tokens

Comparing against 337 models in the database

Category Scores

academia#7 marketing#9 programming#10

Benchmark Tests

View Other Benchmarks

HLE

29.4

General Knowledge

GPQA

87.8

STEM (Physics, Chemistry, Biology)

SciCode

49.0

Scientific

MMLU-Pro

87.1

General Knowledge

AA Coding Index

39.5

Programming

AAII

46.7

General

Metric	HLE	GPQA	SciCode	MMLU-Pro	AA Coding Index	AAII
Score	29.4	87.8	49.0	87.1	39.5	46.7

Compare with Similar Models

claude-opus-4.5

claude-opus-4.6

gemini-3-flash-preview

claude-sonnet-4.5

gemini-3-pro-preview

claude-sonnet-4

Code Examples

Integration samples and API usage

Code Samples for kimi-k2.5

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="kimi-k2.5",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "kimi-k2.5",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.5",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: kimi-k2.5

Provider: openrouter

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from openrouter

kimi-k2.5

kimi-k2.5

Access kimi-k2.5 through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

cogito-v2.1-671b

command-a

kimi-k2.5 by openrouter - AI Model Details, Pricing, and Performance Metrics

kimi-k2.5

kimi-k2.5

Access kimi-k2.5 through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

cogito-v2.1-671b

command-a