Kimi K2.5 API

moonshot/kimi-k2-5
Designed for complex workflows, agentic automation, and long-context reasoning, K2.5 transforms research, document processing, and software development.
Context
256K tokens
Input
$0.78 / 1M tokens
Output
$3.9 / 1M tokens
Released
Feb 6, 2026

How to use Kimi K2.5 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to moonshot/kimi-k2-5.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "moonshot/kimi-k2-5",
      "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": "moonshot/kimi-k2-5",
    "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":"moonshot/kimi-k2-5","messages":[{"role":"user","content":"Hello!"}]}'

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

Kimi K2.5 API Pricing

TypePrice
Input
$0.78 / 1M tokens
Output
$3.9 / 1M tokens
Cached input
$0.13 / 1M tokens

Kimi K2.5 Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Humanity's Last Exam
30.1%
Expert-level questions across many domainsSourceJuly 12, 2026
Terminal-Bench
50.8%
Autonomous shell/terminal task completionSourceJuly 12, 2026
LiveCodeBench
85%
Contamination-free competitive programming problemsSourceJuly 12, 2026
GPQA Diamond
87.6%
Google-proof graduate science questions (hardest subset)SourceJuly 12, 2026
AIME 2025
96.1%
Competition mathematics (AIME), 2025SourceJuly 12, 2026
SWE-bench Verified
76.8%
Resolving verified real GitHub issuesSourceJuly 12, 2026
Intelligence
23.5
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Coding
46.8
Composite score across standardised coding evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

Kimi K2.5 vs other models

ModelInputOutputContextBest for
Kimi K2.5
This page
$0.78 / 1M tokens
$3.9 / 1M tokens
256K tokens
Coding + agents
$6.5 / 1M tokens
$39 / 1M tokens
1M 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
1M tokens
Reasoning + agents

Frequently asked questions

Kimi K2.5 has a 262,144 tokens context window and can return up to 131,000 tokens.

Kimi K2.5 takes image, text as input and returns text.

Use moonshot/kimi-k2-5 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Kimi K2.5 is priced at input $0.78 / 1M tokens, output $3.9 / 1M tokens, cached input $0.13 / 1M tokens.

Yes, Kimi K2.5 can stream responses as they are generated.

Yes, Kimi K2.5 accepts image input alongside text.

Kimi K2.5 was built by Moonshot AI.

Start building with Kimi K2.5

Get API Key
1000+ models, one API.