Skip to content
OpenKey

Kimi K2.6

Moonshot AIReleased Apr 20, 2026

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

Try in playground
Context window
262K tokens
Max output
262K tokens
Input
text, image
Output
text
Tokenizer
Other
Released
Apr 20, 2026
Reasoning
optional

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.550$0.017$0.567
Output$3.20$0.096$3.30
Cache read$0.110$0.0033$0.113

Benchmarks

Artificial Analysis

Intelligence index
42.8
Coding index
56
Agentic index
30.3

Design Arena

CategoryEloWin rateRank
agenticgamedevagents118450.2%#7
agentichtmlslidesagents124859%#2
agenticslidesagents118745.8%#5
agenticslides(html)agents125259.2%#2
agenticslides(python-pptx)agents118645.5%#5
androidnativeagents121250.7%#12
Full-stackagents122356.3%#10
godotgamedevagents121453%#10
htmlslidesagents124958.8%#2
Mobile appsagents122753.1%#9
pptxslidesagents118144.3%#5
python-pptxslidesagents118042.1%#6
Web appsagents125958.2%#7
3Dmodels135562.9%#3
Codemodels132658.1%#7
Data vizmodels130356.8%#9
Game devmodels131658%#12
SVGmodels123452.4%#18
UI componentsmodels132057.2%#10
Websitesmodels131756.3%#8

Head-to-head preference voting. How we filter and rank

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • parallel_tool_calls
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model moonshotai/kimi-k2.6.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k2.6",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="moonshotai/kimi-k2.6",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "moonshotai/kimi-k2.6",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Kimi K2.6 cost via API?
Through OpenKey, Kimi K2.6 costs $0.567 per 1M input tokens and $3.30 per 1M output tokens. That is the provider price ($0.550 / $3.20) plus a flat 3% fee — nothing else.
What is Kimi K2.6's context window?
Kimi K2.6 accepts up to 262K tokens of context and returns up to 262K tokens per request.
Is Kimi K2.6 OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "moonshotai/kimi-k2.6" using any OpenAI SDK — only the base URL and API key change.
What inputs does Kimi K2.6 support?
Kimi K2.6 accepts text, image input and produces text output.

More from Moonshot AI

All Moonshot AI models →