RealRelay.ai
Moonshot AI

kimi-k3.1-pro-highspeed

The high-speed variant of Kimi K3.1 Pro — same intelligence, about 2-3× the speed.

Starting at
Input
$4.00/ 1M
Output
$20.00/ 1M
Open dashboard

Channel

Each channel is compared at its lowest input-price tier; output breaks ties. A dash means /api/pricing does not provide that rate. Selecting a channel updates the endpoints and call example below.

moonshotai/kimi-k3.1-pro-highspeed
Input
$4.00 USD per 1M tokens
Output
$20.00 USD per 1M tokens
Cache read
$0.20 USD per 1M tokens
Cache write
$4.00 USD per 1M tokens

Endpoints

POST/v1/chat/completionsChat Completions

API call spec

This channel does not yet have a verified API parameter specification. See the API docs for request examples.

Call it

Using moonshotai/kimi-k3.1-pro-highspeed

from openai import OpenAIclient = OpenAI(    base_url="https://www.realrelay.ai/v1",    api_key="sk-***",)response = client.chat.completions.create(    model="moonshotai/kimi-k3.1-pro-highspeed",    messages=[{"role": "user", "content": "Hello"}],)print(response.choices[0].message.content)
import OpenAI from "openai";const client = new OpenAI({  baseURL: "https://www.realrelay.ai/v1",  apiKey: process.env.REALRELAY_API_KEY,});const response = await client.chat.completions.create({  model: "moonshotai/kimi-k3.1-pro-highspeed",  messages: [{ role: "user", content: "Hello" }],});console.log(response.choices[0].message.content);
curl https://www.realrelay.ai/v1/chat/completions \  -H "Authorization: Bearer $REALRELAY_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "moonshotai/kimi-k3.1-pro-highspeed",    "messages": [{ "role": "user", "content": "Hello" }]  }'

Prices and availability as published on Oct 23, 2026.

Capabilities

ReasoningTool use
Input
TextImageVideo
Output
Text

Frequently asked questions

What is kimi-k3.1-pro-highspeed?
kimi-k3.1-pro-highspeed is a model from Moonshot AI. RealRelay.ai serves it through one OpenAI-compatible API.
How much does kimi-k3.1-pro-highspeed cost?
kimi-k3.1-pro-highspeed costs from $4.00 per 1M input tokens and $20.00 per 1M output tokens. Pricing is tiered, and this is the starting tier.
What inputs and outputs does kimi-k3.1-pro-highspeed support?
Input: Text, Image, and Video. Output: Text.
What is the context window of kimi-k3.1-pro-highspeed?
kimi-k3.1-pro-highspeed has a context window of 1M tokens. It returns up to 1M output tokens.
What can kimi-k3.1-pro-highspeed do?
Listed capabilities: Reasoning and Tool use.
How do I call kimi-k3.1-pro-highspeed through the API?
Use the model ID moonshotai/kimi-k3.1-pro-highspeed with a RealRelay.ai API key on the OpenAI-compatible API.

More from Moonshot AI

All 6 Moonshot AI models