Kimi-K3.1-Pro API

What is Kimi-K3.1-Pro?

Use the public identifier di-moonshotaikimi-k31-pro-cbc991fefe for Kimi-K3.1-Pro in ServerNet. The gateway uses this identifier to select the configured route; the developer is moonshotai.

Where to use Kimi-K3.1-Pro

• Add Kimi-K3.1-Pro to a support assistant that receives the relevant conversation as text.
• Test Kimi-K3.1-Pro on summaries and extraction using your own documents, with a small output limit first.
• Compare answer quality, total token usage and cost per completed task before choosing Kimi-K3.1-Pro for production.

Model description

Original catalogue description in English. It describes the model; the gateway limits and availability on this page define what you can request here.

Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series. With a 1-million-token context window, Kimi K3.1 Pro delivers substantial improvements in coding, 3D creation, financial research, factual accuracy, and other agentic capabilities.

Build your integration

Send system and user messages, set max_tokens and store X-Request-Id with your usage record. Stream only when this route supports it. Function calls describe actions for your application to run; the gateway does not execute your tools.

Inputs and service limits

The current chat route accepts text only and one completion per request. Images, audio and hosted paid tools are not enabled by the source model’s capabilities. The configured context and output limits may be below the developer’s maximum. Test language quality on your own dataset.

A request cost example

For 1,000 input tokens and 500 output tokens, without a cache discount. This is a catalogue estimate, not a fixed request fee. Reported consumption and the price frozen for your request determine the usage amount.

Estimated usage, Toman

2,051

Plan your token usage

Estimate from the displayed uncached token rates. This is a planning calculation; final billing follows actual usage and the applicable request contract.

Connect to Kimi-K3.1-Pro API

Enable ai:chat on your key and ai:models:read to check availability. Set SERVERNET_API_KEY in your server environment. Change the idempotency key for each new request; keep it unchanged only for an identical retry.

curl https://servernet.cloud/v1/chat/completions \
  -H "Authorization: Bearer $SERVERNET_API_KEY" \
  -H 'Content-Type: application/json' \
  -H 'Idempotency-Key: CHANGE_FOR_EACH_NEW_REQUEST' \
  -d '{
    "model": "di-moonshotaikimi-k31-pro-cbc991fefe",
    "messages": [
        {
            "role": "user",
            "content": "Hello"
        }
    ],
    "max_tokens": 128
}'

import json, os, urllib.request
from uuid import uuid4

body = json.loads("{\n    \"model\": \"di-moonshotaikimi-k31-pro-cbc991fefe\",\n    \"messages\": [\n        {\n            \"role\": \"user\",\n            \"content\": \"Hello\"\n        }\n    ],\n    \"max_tokens\": 128\n}")
request = urllib.request.Request(
    "https://servernet.cloud/v1/chat/completions",
    data=json.dumps(body).encode(),
    headers={
        "Authorization": "Bearer " + os.environ["SERVERNET_API_KEY"],
        "Content-Type": "application/json",
        "Idempotency-Key": str(uuid4()),
    },
    method="POST",
)
with urllib.request.urlopen(request) as response:
    print(json.load(response))

import { randomUUID } from 'node:crypto';

const response = await fetch('https://servernet.cloud/v1/chat/completions', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer ' + process.env.SERVERNET_API_KEY,
    'Content-Type': 'application/json',
    'Idempotency-Key': randomUUID(),
  },
  body: JSON.stringify({
    "model": "di-moonshotaikimi-k31-pro-cbc991fefe",
    "messages": [
        {
            "role": "user",
            "content": "Hello"
        }
    ],
    "max_tokens": 128
}),
});
if (!response.ok) throw new Error('HTTP ' + response.status);
console.log(await response.json());

Use the same Idempotency-Key when retrying an identical request. Successful responses are replayed without a second charge for 24 hours. Do not automatically retry when x-should-retry:false is present. The key is shown once. Store it in a server environment variable. Keep it out of browser code, GitHub and logs.

Compare models for the same task