What is MoonshotAI: Kimi K2.6's context window?

MoonshotAI: Kimi K2.6 supports a context window of 262,144 tokens, allowing you to process large documents and maintain long conversations.

How to use MoonshotAI: Kimi K2.6 API via Ofox?

Simply set your base URL to https://api.ofox.ai/v1 and use your Ofox API key. The API is OpenAI-compatible — just change the base URL and API key in your existing code.

MoonshotAI: Kimi K2.6

Name: MoonshotAI: Kimi K2.6
Brand: moonshotai
Price: 0.95 USD
Availability: InStock

Chat

moonshotai/kimi-k2.6

Compare Try in Playground Get started

Kimi K2.6 is Moonshot's latest and most intelligent model, with major improvements in general agentic tasks, coding, and visual understanding. It achieves top scores on PhD-level science benchmarks (full GPQA Diamond) and advanced reasoning challenges, with a 262K context and output window. Available via OpenAI and Anthropic protocols.

Context Window

262K

Max Output Tokens

262K

Released

2026-04-21

Capabilities

VisionFunction CallingReasoningPrompt CachingWeb Search

Available Providers

MoonshotAzureAliyun

Supported Protocols

openaianthropic

Providers

Aliyunprovider.type: "aliyun"

Input Tokens

$0.95/M

Output Tokens

$4/M

Cache Read

$0.2/M

Cache Write

$1.17/M

Web Search

$0.01/R

Protocols

anthropic

Azureprovider.type: "azure_foundry"

Input Tokens

$0.95/M

Output Tokens

$4/M

Cache Read

$0.16/M

Web Search

$0.035/R

Protocols

openai/v1/chat/completions/v1/responses

anthropic

Moonshotprovider.type: "moonshot"

Input Tokens

$0.95/M

Output Tokens

$4/M

Cache Read

$0.16/M

Web Search

$0.005/R

Protocols

openai/v1/chat/completions

anthropic

Playground

Open in OfoxChat

Code Examples

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ofox.ai/v1",
    api_key="YOUR_OFOX_API_KEY",
)

response = client.chat.completions.create(
    model="moonshotai/kimi-k2.6",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

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

Uptime & Status

Benchmarks

LMArena ↗Evaluated as kimi-k2.6

MoonshotAI: Kimi K2.6 scores 1462 in the Overall category of the LMArena text leaderboard (style control), ranking #37 of 374 models based on 36,570 human preference votes (updated 2026-07-12).

Benchmark scores for kimi-k2.6 on LMArena
Category	Arena Score	95% CI	Rank	Votes
Overall	1462	1457–1467	#37 of 374	36,570
Hard Prompts	1486	1481–1492	#35 of 374	23,599
Coding	1515	1508–1522	#25 of 369	10,075
Math	1479	1466–1493	#17 of 362	1,882
Creative Writing	1432	1423–1441	#46 of 372	5,722
Instruction Following	1456	1449–1463	#34 of 374	11,791
Chinese	1530	1515–1545	#7 of 344	1,818

Source: LMArena · CC BY 4.0 · Updated 2026-07-12 · Methodology ↗ · Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.