Kimi K2 Thinking API

moonshotai/kimi-k2-thinking
Kimi K2 Thinking on AIMLAPI.
Context
262K tokens
Input
$0.82524 / 1M tokens
Output
$3.4385 / 1M tokens

How to use Kimi K2 Thinking API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to moonshotai/kimi-k2-thinking.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "moonshotai/kimi-k2-thinking",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "moonshotai/kimi-k2-thinking",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"moonshotai/kimi-k2-thinking","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Kimi K2 Thinking API Pricing

TypePrice
Input
$0.82524 / 1M tokens
Output
$3.4385 / 1M tokens
Cached input
$0.20631 / 1M tokens

Kimi K2 Thinking Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
SWE-bench Verified
71.3%
Resolving verified real GitHub issuesSourceJuly 8, 2026
Humanity's Last Exam
44.9%
Expert-level questions across many domainsSourceJuly 8, 2026
Intelligence
22
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Math
94.7
Composite score across standardised mathematics evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

Kimi K2 Thinking vs other models

ModelInputOutputContextBest for
$0.82524 / 1M tokens
$3.4385 / 1M tokens
262K tokens
Reasoning + agents
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

Kimi K2 Thinking has a 262,144 tokens context window and can return up to 100,352 tokens.

Kimi K2 Thinking takes image, text as input and returns text.

Use moonshotai/kimi-k2-thinking as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Kimi K2 Thinking is priced at input $0.82524 / 1M tokens, output $3.4385 / 1M tokens, cached input $0.20631 / 1M tokens.

Yes, Kimi K2 Thinking can stream responses as they are generated.

Yes, Kimi K2 Thinking accepts image input alongside text.

Kimi K2 Thinking was built by Moonshot AI.

Start building with Kimi K2 Thinking

Get API Key
1000+ models, one API.