kimi-k2

completions

On:parasailgroq

kimi-k2

completions

Published by: moonshotaiProviders:

parasail groq

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.

Provider	Input	Output	Cached
parasail	$0.99 / 1M tokens	$2.99 / 1M tokens	-
groq	$1 / 1M tokens	$3 / 1M tokens	$0.5 / 1M tokens

Released

Jan 1, 2025

Knowledge

Jul 5, 2024

Context

131072

Input

$0.99 / 1M tokens

Output

$2.99 / 1M tokens

Accepts: text

Returns: text

Providers	Context	Input Price	Cached	Output Price	Input Formats	Output Formats	License
parasail	131072 tokens	$0.99 / 1M tokens	_	$2.99 / 1M tokens	text	text	Modified MIT License
groq	131072 tokens	$1 / 1M tokens	$0.5 / 1M tokens	$3 / 1M tokens	text	text	Proprietary

Released Jan 1, 2025Knowledge Cutoff: Jul 5, 2024

Access kimi-k2 through LangDB AI Gateway

Recommended

Integrate with moonshotai's kimi-k2 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

Available from 2 providers

Provider:

Benchmark Results for kimi-k2

Category Performance Scores:

Academia: Score 63.33 (Top 14% - Rank #47)
Finance: Score 53.85 (Top 25% - Rank #84)
Marketing: Score 57.60 (Top 20% - Rank #67)
Maths: Score 57.30 (Top 36% - Rank #121)
Programming: Score 38.10 (Top 33% - Rank #111)
Science: Score 70.79 (Top 21% - Rank #71)
Writing: Score 56.12 (Top 28% - Rank #94)

Overall Performance: 56.726666666666674 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AA Coding Index	38.10	Top 33%	Programming
AAII	50.40	Top 14%	General
AA Math Index	57.30	Top 36%	Mathematics
GPQA	76.25	Top 19%	STEM (Physics, Chemistry, Biology)
HLE	6.30	Top 28%	General Knowledge
HumanEval	94.50	Top 0%	Programming
LiveCodeBench	61.00	Top 21%	Programming
MMLU	90.20	Top 4%	General Knowledge
MMLU-Pro	82.20	Top 18%	General Knowledge
SciCode	30.70	Top 44%	Scientific

MMLU Score: 90.20 - Massive Multitask Language Understanding benchmark

HumanEval Score: 94.50 - Coding capability benchmark

GPQA Score: 76.25 - Graduate-level reasoning benchmark

Model Comparison:

Provider: parasail

Model Type: completions

Context Size: 131072 tokens

Comparing against 335 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AA Coding Index

38.1

Programming

AAII

50.4

General

AA Math Index

57.3

Mathematics

GPQA

76.3

STEM (Physics, Chemistry, Biology)

HLE

6.3

General Knowledge

HumanEval

94.5

Programming

LiveCodeBench

61.0

Programming

MMLU

90.2

General Knowledge

MMLU-Pro

82.2

General Knowledge

SciCode

30.7

Scientific

Metric	AA Coding Index	AAII	AA Math Index	GPQA	HLE	HumanEval	LiveCodeBench	MMLU	MMLU-Pro	SciCode
Score	38.1	50.4	57.3	76.3	6.3	94.5	61.0	90.2	82.2	30.7

Compare with Similar Models

gemini-2.5-pro-preview

Code Examples

Integration samples and API usage

Code Samples for kimi-k2

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",
    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",
    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",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: kimi-k2

Provider: parasail

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

Create API Key

Related Models

Similar models from parasail

kimi-k2

kimi-k2

Access kimi-k2 through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

anubis-70b-v1.1

anubis-pro-105b-v1

codellama-7b-instruct-solidity

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-r1-0528

kimi-k2 by parasail - AI Model Details, Pricing, and Performance Metrics

kimi-k2

kimi-k2

Access kimi-k2 through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

anubis-70b-v1.1

anubis-pro-105b-v1

codellama-7b-instruct-solidity

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-r1-0528