MoonshotFree
Kimi K2.6 Thinking
API model name: kimi-k2.6-thinking
Kimi K2.6 Thinking is Moonshot's chat model, served on the Api.Airforce unified API. It has a 262K-token context window. Capabilities include Tool calling, Reasoning, Prompt caching. It is available on the free tier at no per-token cost. Knowledge cutoff: 2026-02. Access it through the OpenAI-compatible API with one key, alongside 100+ other models on Api.Airforce.
Pricing
Specifications
- Provider
- Moonshot
- Type
- chat model
- Context window
- 262K tokens
- Max output
- 16K tokens
- Knowledge cutoff
- 2026-02
- Input
- text
- Output
- text
- Prompt caching
- Supported
Capabilities
Tool callingReasoningPrompt cachingStreaming
Benchmarks
Independent evaluations and measured speed from Artificial Analysis.
Intelligence Index
42.9/100
Coding Index
38.4/100
GPQA Diamond79%
Humanity's Last Exam18%
Output speed32.4 tok/s
Time to first token1.46 s
Source: Benchmark data by Artificial Analysis (artificialanalysis.ai)
What is Kimi K2.6 Thinking used for?
- Chatbots & assistants — conversational AI, drafting, summarizing and Q&A.
- Agents & automation — function calling and tool use for multi-step workflows.
- Complex reasoning — math, coding and step-by-step problem solving.
- Long-context tasks — process entire documents or codebases in a single prompt.
- Real-time experiences — stream tokens for responsive chat and apps.
Kimi K2.6 Thinking vs. similar models
| Model | Intelligence | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| Kimi K2.6 Thinking | 42.9 | 262K | Free | Free |
| Kimi K2 | 26.3 | 131K | $0.87 | $3.42 |
| Kimi K2 0711 | — | — | $0.87 | $3.42 |
| Kimi K2 0905 | — | — | $2.46 | $10.20 |
Prices are Api.Airforce pay-as-you-go rates per 1M tokens. Context is the maximum input length.
Related models
Kimi K2Moonshot · $0.87 / 1MKimi K2 0711Moonshot · $0.87 / 1MKimi K2 0905Moonshot · $2.46 / 1MKimi K2 TurboMoonshot · $3.42 / 1MKimi K2.5Moonshot · $0.58 / 1MKimi K2.5 FreeMoonshot · FreeKimi K2.6Moonshot · $0.55 / 1MKimi K2.7 CodeMoonshot · $0.55 / 1MMoonshot V1 128kMoonshot · $4.26 / 1MMoonshot V1 128k VisionMoonshot · $4.26 / 1MMoonshot V1 32kMoonshot · $2.13 / 1MMoonshot V1 32k VisionMoonshot · $2.13 / 1M
Kimi K2.6 Thinking — frequently asked questions
- How much does Kimi K2.6 Thinking cost?
- Kimi K2.6 Thinking is available on the free tier at no token cost — create an API key and start building. Paid plans add higher rate limits.
- What is the context window of Kimi K2.6 Thinking?
- Kimi K2.6 Thinking supports a context window of up to 262K tokens. It can return up to 16K tokens in a single response.
- What can Kimi K2.6 Thinking do?
- Kimi K2.6 Thinking supports Tool calling, Reasoning, Prompt caching.
- Is Kimi K2.6 Thinking free to use?
- Yes — Kimi K2.6 Thinking is on the free tier. You can use it with an Api.Airforce API key at no cost.
- How do I use Kimi K2.6 Thinking via the API?
- Kimi K2.6 Thinking is OpenAI-compatible. Point any OpenAI SDK at https://api.airforce/v1 and pass the model ID kimi-k2.6-thinking with your Api.Airforce API key.
- Who makes Kimi K2.6 Thinking?
- Kimi K2.6 Thinking is Moonshot's chat model, served through the unified Api.Airforce gateway alongside 100+ other models.
Loading live metrics…
Loading live metrics…
Loading live metrics…
Use Kimi K2.6 Thinking via the API
OpenAI-compatible — point any OpenAI SDK at https://api.airforce/v1 and pass kimi-k2.6-thinking as the model.
cURL
curl https://api.airforce/v1/chat/completions \
-H "Authorization: Bearer $AIRFORCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k2.6-thinking",
"messages": [{ "role": "user", "content": "Hello!" }]
}'Python
from openai import OpenAI
client = OpenAI(base_url="https://api.airforce/v1", api_key="$AIRFORCE_API_KEY")
r = client.chat.completions.create(
model="kimi-k2.6-thinking",
messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airforce/v1", apiKey: process.env.AIRFORCE_API_KEY });
const r = await client.chat.completions.create({
model: "kimi-k2.6-thinking",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(r.choices[0].message.content);