Routeway Logo
Back to Models
MoonshotAI

Kimi K2 Thinking

Available

Description

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift. It sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.

At a Glance

Key pricing and model details available for this model.

Input price

$0.30

per 1M tokens

Output price

$2.00

per 1M tokens

Context window

262K

tokens

Hallucination rate

1.6%

Token Pricing

Token pricing normalized to per-million-token rates.

Input / 1M tokens

$0.30

Output / 1M tokens

$2.00

Cache Read / 1M tokens

Free

Token Pricing Details

Rates are shown per 1M tokens for easier comparison.

Input / 1M tokens$0.30
Input unit1M tokens
Output / 1M tokens$2.00
Output unit1M tokens
Cache Read / 1M tokensFree
Cache Read unit1M tokens

Feature Availability

Capabilities explicitly listed in the current payload.

LLM

Available

Yes

Vision

Not listed

No

Function calling

Available

Yes

Reasoning

Available

Yes

Supported Parameters

frequency_penalty
logit_bias
max_completion_tokens
presence_penalty
reasoning_effort
response_format
stop
temperature
tool_choice
tools
top_p

Artificial Analysis

Index scores currently reported for this model.

Intelligence Index

40.9

Coding Index

34.8

Math Index

94.7

Category Radar

Aggregated from the benchmark values present for reasoning, code, math, and accuracy.

Benchmark Breakdown

Detailed benchmark results drawn from the current payload.

Intelligence Index

index

Overall 'how smart' score for an AI, combining reasoning, math, coding, and knowledge.

40.9

Reported score

Coding Index

index

How well the model handles real programming tasks.

34.8

Reported score

Math Index

index

Composite score measuring mathematical reasoning and problem-solving.

94.7

Reported score

MMLU-Pro

reasoning

A broad and difficult knowledge-and-reasoning benchmark across many subjects.

84.8%

Reported score

GPQA

reasoning

Graduate-level science questions designed to be difficult to shortcut.

83.8%

Reported score

HLE

reasoning

A very hard expert-level exam across a wide range of subjects.

22.3%

Reported score

LiveCodeBench

code

Fresh programming tasks meant to test current coding ability.

85.3%

Reported score

SciCode

code

Coding tasks drawn from real scientific workflows.

42.4%

Reported score

AIME 2025

math

The 2025 AIME benchmark used to reduce data leakage concerns.

94.7%

Reported score

IFBench

accuracy

Measures how precisely the model follows detailed instructions.

68.1%

Reported score

LCR

accuracy

Tests long-context reasoning over large documents and conversations.

66.3%

Reported score

TerminalBench Hard

code

A harder coding-agent benchmark for complex multi-step terminal tasks.

31.1%

Reported score

Tau2

accuracy

Evaluates realistic agent behavior in tool-using support workflows.

93%

Reported score

Code Samples

Quick start with the Routeway API

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: "https://api.routeway.ai/v1",
  apiKey: "<YOUR_API_KEY>",
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "kimi-k2-thinking",
    messages: [
      {
        role: "user",
        content: "Explain quantum computing in simple terms"
      }
    ]
  });

  console.log(completion.choices[0].message);
}

main();