Moonshot AI: Kimi K2 Thinking
moonshotai/kimi-k2-thinking
Access Kimi K2 Thinking from Moonshot AI using Puter.js AI API.
Get Started// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "moonshotai/kimi-k2-thinking"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "moonshotai/kimi-k2-thinking"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="moonshotai/kimi-k2-thinking",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "moonshotai/kimi-k2-thinking",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
Kimi K2 Thinking is Moonshot AI's reasoning-enhanced variant of Kimi K2, trained to interleave step-by-step chain-of-thought with dynamic tool calls. It supports up to 200–300 sequential tool calls without drift, enabling deep autonomous research, coding, and analysis workflows.
It achieves 71.3% on SWE-bench Verified, 44.9% on Humanity's Last Exam (with tools), 60.2% on BrowseComp, and 99.1% on AIME 2025 (with Python) — placing it among the top open-source thinking models. It uses native INT4 quantization and a 256K context window.
K2 Thinking is designed for complex, multi-step tasks where extended reasoning and sustained tool orchestration matter more than low-latency responses.
Context Window 262K
tokens
Max Output 100K
tokens
Input Cost $0.6
per million tokens
Output Cost $2.5
per million tokens
Release Date Nov 6, 2025
Output Speed 132
tokens / sec
Latency 0.81s
time to first token
Model Playground
Try Kimi K2 Thinking instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Kimi K2 Thinking performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 83.8% |
| Humanity's Last Exam Cross-domain reasoning | 22.3% |
| LiveCodeBench Recent coding problems | 85.3% |
| SciCode Scientific programming | 42.4% |
| AIME 2025 Advanced math exam | 94.7% |
| IFBench Instruction following | 68.1% |
| LCR Long-context reasoning | 66.3% |
| Terminal-Bench Hard Agentic terminal tasks | 31.1% |
| τ²-Bench Tool use / agents | 93.0% |
Scores sourced from Artificial Analysis.
Find other Moonshot AI models →
Kimi K3
Kimi K3 is Moonshot AI's flagship open-weight model, released July 16, 2026, with full weights following on July 27. At roughly 2.8 trillion parameters in a Mixture-of-Experts architecture, Moonshot positions it as the largest open-source model released to date, built on two new components: Kimi Delta Attention, a hybrid linear attention mechanism, and Attention Residuals, a replacement for standard residual connections. It runs in an always-on thinking mode with a 1-million-token context window and accepts text, image, and video input. Reported results include 93.5% on GPQA Diamond, 91.2% on BrowseComp, 88.3% on Terminal-Bench 2.1, and a first-place finish on Arena.ai's Frontend Code Arena, putting it close to Claude Opus 4.8 and GPT-5.5 on several agentic and coding tasks. These figures come from Moonshot and early testers, not independently confirmed leaderboards. It suits developers building long-horizon coding agents and tool-calling pipelines who want frontier-level performance at open-weight pricing.
ChatKimi K2.7 Code
Kimi K2.7 Code is Moonshot AI's open-weight coding-agent model, released June 2026 and purpose-built for long-horizon, autonomous coding tasks. It shares the same 1-trillion-parameter Mixture-of-Experts architecture (32B active parameters) as K2.6 but is entirely focused on software engineering workloads. Compared to K2.6, it improves 21.8% on Kimi Code Bench v2, 11% on Program Bench, and 31.5% on MLS Bench Lite, while cutting reasoning-token usage by roughly 30%. It always runs in thinking mode — non-thinking mode is not supported. With a 262K-token context window, K2.7 Code is well-suited for multi-file, repository-scale coding pipelines and agentic workflows where sustained reasoning and deep code understanding matter.
ChatKimi K2.6
Kimi K2.6 is Moonshot AI's latest open-weight multimodal model, built on a 1-trillion-parameter mixture-of-experts architecture with a 256K context window. It excels at agentic coding and long-horizon execution, supporting sustained autonomous workflows with 4,000+ tool calls across languages like Rust, Go, and Python. On key benchmarks, it scores 58.6 on SWE-Bench Pro, 54.0 on HLE with Tools, and 50.0 on Toolathlon — competitive with GPT-5.4 and Claude Opus 4.6 on coding and agent tasks, though trailing them on pure reasoning. The model accepts text, image, and video input, supports both thinking and non-thinking modes, and offers an OpenAI-compatible API. It's a strong pick for developers building multi-step agentic workflows and complex software engineering pipelines.
Frequently Asked Questions
You can access Kimi K2 Thinking by Moonshot AI through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Kimi K2 Thinking to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0.6 |
| Output | $2.5 |
Kimi K2 Thinking was created by Moonshot AI and released on Nov 6, 2025.
Kimi K2 Thinking supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Kimi K2 Thinking can generate up to 100K tokens in a single response.
Kimi K2 Thinking scores 32.7 on the Artificial Analysis Intelligence Index, outperforming 80% of tracked models. On math, it scores 94.7 (outperforms 96% of models).
Yes — the Kimi K2 Thinking API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add Kimi K2 Thinking to your app without worrying about API keys or setup.
Read the Docs View Tutorials