Kimi K2 0711 API

moonshotai/kimi-k2
Kimi K2 0711 on AIMLAPI.
Context
128K tokens
Input
$0.783978 / 1M tokens
Output
$3.16342 / 1M tokens
Released
Jul 11, 2025

How to use Kimi K2 0711 API

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

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "moonshotai/kimi-k2",
      "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",
    "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","messages":[{"role":"user","content":"Hello!"}]}'

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

Kimi K2 0711 API Pricing

TypePrice
Input
$0.783978 / 1M tokens
Output
$3.16342 / 1M tokens

Kimi K2 0711 Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
GPQA Diamond
75.1%
Google-proof graduate science questions (hardest subset)SourceJuly 8, 2026
AIME 2025
49.5%
Competition mathematics (AIME), 2025SourceJuly 8, 2026
LiveCodeBench
53.7%
Contamination-free competitive programming problemsSourceJuly 8, 2026
SWE-bench Verified
65.8%
Resolving verified real GitHub issuesSourceJuly 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

Frequently asked questions

Kimi K2 0711 has a 131,072 tokens context window and can return up to 100,352 tokens.

Kimi K2 0711 takes image, text as input and returns text.

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

Kimi K2 0711 is priced at input $0.783978 / 1M tokens, output $3.16342 / 1M tokens.

Yes, Kimi K2 0711 can stream responses as they are generated.

Yes, Kimi K2 0711 accepts image input alongside text.

Kimi K2 0711 was built by Moonshot AI.

Yes, it supports tool calling, including parallel tool calls, as part of its feature set.

It offers reasoning, function calling, structured outputs, vision input, and web search alongside standard text chat and streaming.

Start building with Kimi K2 0711

Get API Key
1000+ models, one API.