Kimi API pricing. Up to 60% below list.

Kimi is Moonshot AI's family of open-weight models. Kimi K3.1 Pro, released in October 2026, is the newest flagship: Kimi K3 trained further with reinforcement learning, for coding agents, 3D work and financial research. Kimi K3.1 Pro Highspeed is the same model at two to three times the speed, and Kimi K3 is the 2.8-trillion-parameter model both are built on. All three hold 1M tokens of context and read images. Zurelay serves them through one OpenAI-compatible endpoint, below Moonshot's list price.

Kimi models
3
Below Moonshot AI's list
18–60%
From, per 1M input
$0.80
Get your API keySee every price
PlaygroundDemo

Chat with Kimi K3.1 Pro

Pick a prompt to see a reply stream in, priced at Kimi K3.1 Pro’s rate.

Sample replies, priced live. Nothing is sent.

Pricing

Every Kimi model. Live prices, one key.

Each Kimi model on Zurelay, with Moonshot AI's list price beside ours.

Kimi API prices on Zurelay and at Moonshot AI's list price
ModelContextInput / 1MOutput / 1M10K requestsYou save
Kimi K3.1 Prokimi-k3.1-pro1M
$0.80
$2.00
$4.00
$10.00
$36.00
$90.00
60%off
Kimi K3.1 Pro Highspeedkimi-k3.1-pro-highspeed1M
$3.30
$4.00
$16.50
$20.00
$148.50
$180.00
18%off
Kimi K3kimi-k31M
$1.27
$3.00
$6.37
$15.00
$57.25
$135.00
58%off

Prices in US dollars per 1M tokens, live from the catalog, with Moonshot AI's list price struck through. 10K requests is 10,000 requests of 2,000 tokens in and 500 out, at each price. You save is on output tokens.

Which model

Which Kimi model to use. Same key for all of them.

60%off

Coding agents and deep work

Kimi K3.1 Pro

$0.80 / $4.00 per 1M tokens

Moonshot's newest flagship, released in October 2026: 65.7% on Terminal-Bench 4.0, strong at 3D and financial work, and a lower list price than K3.

Kimi K3.1 Pro API
18%off

Fast answers

Kimi K3.1 Pro Highspeed

$3.30 / $16.50 per 1M tokens

The same K3.1 Pro model at two to three times the speed, for chat and interactive agents where someone is waiting.

Kimi K3.1 Pro Highspeed API
58%off

Prompts tuned on K3

Kimi K3

$1.27 / $6.37 per 1M tokens

Moonshot's July 2026 flagship, 2.8 trillion parameters with native vision, which K3.1 Pro is built on.

Kimi K3 API

Quickstart

Change two lines. Keep your code.

Point the OpenAI SDK, or any OpenAI-compatible tool, at https://api.zurelay.com/v1 and use your Zurelay key. Streaming, tool calling and structured output work as documented.

Add credit from $10, with no subscription. The quickstart has the rest.

chat.py
from openai import OpenAI
client = OpenAI(
    base_url="https://api.zurelay.com/v1",
    api_key="YOUR_ZURELAY_KEY",
)
stream = client.chat.completions.create(
    model="kimi-k3.1-pro",
    messages=[{"role": "user", "content": "Explain quicksort in two sentences."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

Verified

The Kimi you asked for. Checked every day.

Model capacity is often bought ahead, through prepaid credits, committed-spend contracts and volume tiers, and not all of it gets used. Sellers offer it below list price. Zurelay tests each route, pools several per model and sends every request to one that is available and verified.

Before a route serves requests, and every day after, it has to pass identity, dated-knowledge and reasoning checks that catch a different or older model sold under a newer name. Failed attempts move to another route, and you aren’t billed for them. How models are verified.

Live health for every model is on the status page.

FAQ

Kimi API questions.

Anything else? Ask our team and we’ll answer by email.

How much does the Kimi API cost?

On Zurelay, Kimi models cost from $0.80 input and $4.00 output per 1M tokens (Kimi K3.1 Pro) to $3.30 and $16.50 (Kimi K3.1 Pro Highspeed), 18–60% below Moonshot AI's list prices. There's no subscription or minimum spend: you add prepaid credit from $10 and pay for the tokens you use.

Is it the real Kimi?

Yes. Each model is served over several routes run by independent sellers. Every route is tested before it serves requests and every day after, with identity, dated-knowledge and reasoning checks that catch a different or older model sold under the name you asked for. If an answer doesn't look right, send its x-request-id to support and we check the route that served it.

Why is it cheaper than Moonshot AI's own API?

Sellers offer model capacity they bought ahead, through prepaid credits, committed-spend contracts and volume tiers, below list price. Zurelay tests it, pools several routes per model and sends each request to one that is available and verified. Requests aren't served under Moonshot AI's own terms for its customers; our Terms explain how they are served.

How do I start calling Kimi through Zurelay?

Create a key, then point the OpenAI SDK, or any OpenAI-compatible tool, at https://api.zurelay.com/v1 with a model ID such as kimi-k3.1-pro. Code that already uses the OpenAI SDK only needs the base URL, the key and the model name changed.

What's the difference between Kimi K3.1 Pro and Kimi K3.1 Pro Highspeed?

They are the same model, and Moonshot says they are equally capable. Highspeed writes two to three times faster, about 97 tokens a second against 46 in our tests, and costs more. Use Highspeed when someone is waiting on the answer, and K3.1 Pro for background work.

More pricing

Stop paying list price.
Start saving today.

Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.

Get your API keyTalk to an engineer