How to Access and Use Kimi K3.1 Pro Through Moonshot’s API and Playground

Some links on this page are affiliate links: if you buy through them we may earn a commission, at no extra cost to you.

To access Kimi K3.1 Pro officially, sign in to Moonshot AI’s Kimi API Platform, add at least $1 to your account, create an API key, and try the model in the Playground or call it through the API. For the OpenAI-compatible API, use the base URL https://api.moonshot.ai/v1 and the model ID kimi-k3.1-pro. Keep the key private and out of client-side code.

What is the official way to access Kimi K3.1 Pro?

Moonshot AI’s Kimi API Platform is the official route described for K3.1 Pro. It gives you a Playground for testing prompts and an API key for using the model from software. A successful top-up of at least $1 is required to unlock K3.1 Pro; that is an access threshold, not a statement that every request costs $1.

#	Preview	Product	Price
1		MINISFORUM MS-02 Ultra Workstation Mini PC, Intel Core Ultra 9 285HX (24C/24T, up to 5.5GHz), PCIe...	$1,659.00	Buy on Amazon
2		AI WORKSTATION GUIDE: A Practical Handbook for Developers, Data Scientists And Home AI Lab Builders...	$33.69	Buy on Amazon
3		ASRock Radeon AI PRO R9700 Creator 32GB Professional Graphics Card, 2920 MHz Boost Clock, GDDR6, AMD...		Buy on Amazon
4		Apple 2026 MacBook Pro Laptop with Apple M5 Max chip with 18-core CPU and 40-core GPU: Built for AI,...	$4,499.00	Buy on Amazon
5		MINISFORUM MS-S1 MAX Mini AI Workstation PC, AMD Ryzen AI Max+ 395 (16C/32T),RDNA3.5 GPU,128GB...	$3,919.00	Buy on Amazon

As an Amazon Associate I earn from qualifying purchases.

The basic flow is: sign in to the platform, add funds, create a key in API Keys, then either test in the Playground or make an API request. Moonshot’s documentation says the key is displayed for copying once, so store it securely at creation rather than relying on being able to retrieve it later.

1. Open Moonshot AI’s Kimi API Platform and sign in.
2. Complete a successful account top-up of at least $1 to unlock the flagship model.
3. Open API Keys, create a key, and copy it into a secure secret store or environment variable named MOONSHOT_API_KEY.
4. Open the Playground to test a prompt, or configure an API client using the model ID and base URL below.

The Playground is useful for prompt experiments without writing code. Use an API client when you need to integrate K3.1 Pro into an application, automate a workflow, or control how requests are assembled.

#1 Best Overall

MINISFORUM MS-02 Ultra Workstation Mini PC, Intel Core Ultra 9 285HX (24C/24T, up to 5.5GHz), PCIe 5.0 x16, 32GB RAM 1TB SSD,USB4 v2 80Gbps, Dual 25GbE+10GbE+2.5GbE, Wi-Fi 7, 350W PSU

• High-Performance AI Processor: The MS-02 Ultra features an Intel Core Ultra 9 285HX (24C/24T, up to 5.5 GHz, 13 TOPS NPU), delivering fast and efficient performance for AI inference, algorithm development, and media workloads. A PCIe x16 expansion slot supports desktop-class GPU upgrades for advanced model training and accelerated computing tasks, suitable for creators, engineers, and teams handling intensive parallel workloads
• Expandable Memory and Storage Configuration: Four DDR5 SODIMM slots support up to 256 GB of memory, while ECC helps maintain data integrity in mission-critical environments. Four PCIe 4.0 M.2 slots support up to 24 TB of storage, supporting RAID 0/1/5/10, combining high-speed performance with data protection. It allows for the creation of independent scratch disks, media libraries, and project drives, providing high-throughput for production workflows
• Advanced PCIe and USB Connectivity: Up to three PCIe slots can be equipped, including a dual-slot x16 GPU. The main slot supports PCIe 5.0, meeting the needs of high-bandwidth creative and computing workloads. USB 4.0 v2 (80Gbps) supports high-bandwidth external storage and displays
• Ultra-fast Networking Capabilities: Wi-Fi 7 further enhances wireless performance with next-generation speeds and low-latency stability. Intelligent bandwidth switching optimizes throughput in different network environments, ensuring optimal performance for enterprise or local networks. Dual 25GbE ports (providing up to approximately 3.125 GB/s bandwidth, about 25 times faster than traditional 1GbE), enabling seamless large-scale file transfers and parallel computing. 10GbE and 2.5GbE ports, with support for Intel vPro technology, ensure enterprise-grade remote management and deployment flexibility
• Server-grade Thermal Architecture: Utilizing a dedicated CPU/GPU airflow design, equipped with a 6-pipe dual-fan cooler, it maintains stable performance even under sustained loads, delivering up to 140W Turbo power while maintaining a 100W TDP, and operating with noise levels as low as 36 dB. An integrated 350W power supply ensures stable and reliable output for demanding computing tasks and fully loaded extended configurations

$1,659.00

Buy on Amazon

What model name and endpoint should I use?

For direct OpenAI-compatible requests to Moonshot, set the base URL to https://api.moonshot.ai/v1 and send kimi-k3.1-pro as the model. The chat completions route is POST https://api.moonshot.ai/v1/chat/completions.

Moonshot also documents three API styles for production: Chat Completions, Responses, and an Anthropic-compatible Messages API. The code below uses Chat Completions. If an integration expects a different API style, select its corresponding documented interface rather than assuming the routes or request formats are interchangeable.

How do I use Kimi K3.1 Pro with the OpenAI Python SDK?

Install Python 3.9 or later and openai version 1.0 or later, put the API key in the environment, and initialize the SDK with Moonshot’s base URL. The model ID belongs in the request, not in the base URL.

pip install "openai>=1.0"

Set the key in your shell before running the Python program. For example, on macOS or Linux:

Rank #2

AI WORKSTATION GUIDE: A Practical Handbook for Developers, Data Scientists And Home AI Lab Builders on Hardware Selection, GPU Setup, LLM Deployment And Performance Optimization

$33.69

Buy on Amazon

export MOONSHOT_API_KEY="your-api-key"

Then use this minimal request:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["MOONSHOT_API_KEY"],
    base_url="https://api.moonshot.ai/v1",
)

completion = client.chat.completions.create(
    model="kimi-k3.1-pro",
    messages=[
        {"role": "user", "content": "Introduce Kimi K3.1 Pro in one sentence."}
    ],
)
print(completion.choices[0].message.content)

On success, the program prints the text from the model’s first response choice. The example deliberately reads the key from the environment instead of putting it directly in the source file. In deployed applications, use the hosting environment’s secret-management facility and ensure the key is not committed to source control or exposed in browser code.

What does the equivalent HTTP request need?

Send a JSON request to the Chat Completions route with a Bearer API key, a JSON content type, the model ID, and a messages array. The following is a minimal cURL illustration; insert the key through a secure shell environment rather than saving a real key in a script.

curl https://api.moonshot.ai/v1/chat/completions 
  -H "Authorization: Bearer $MOONSHOT_API_KEY" 
  -H "Content-Type: application/json" 
  -d '{
    "model": "kimi-k3.1-pro",
    "messages": [
      {"role": "user", "content": "Introduce Kimi K3.1 Pro in one sentence."}
    ]
  }'

What can Kimi K3.1 Pro do through the API?

Moonshot documents a 1-million-token context window, visual understanding, and support for text, image, and video input. The API also supports multi-turn message history, streaming output, function or tool calls, and JSON mode. Moonshot highlights coding, 3D creation, financial research, and agentic workflows as model strengths; those are provider-described capabilities, not a guarantee of a particular result on every task.

• Long-context work: The listed context window is 1 million tokens. A context window is the model’s available input-and-conversation capacity; it does not mean every integration, request, or account configuration will necessarily accept an arbitrarily large payload.
• Images and video: Vision requests use structured content arrays containing image parts. Do not serialize the image request structure into one plain string; send the supported content structure expected by the API.
• Multi-turn conversations: Include the relevant conversation history in the message sequence when a request needs prior turns. The API supports multi-turn message history.
• Streaming: Streaming is supported when an application needs output incrementally rather than waiting for a complete response.
• Tools and JSON: Function/tool calls and JSON mode are supported for applications that need structured outputs or tool-mediated workflows. Consult the API documentation for the exact request fields and response handling for the chosen mode.

How does K3.1 Pro’s reasoning setting work?

Thinking is always enabled for K3.1 Pro. Moonshot documents a top-level reasoning_effort request field with the values low, high, or max; max is the default.

Rank #3

ASRock Radeon AI PRO R9700 Creator 32GB Professional Graphics Card, 2920 MHz Boost Clock, GDDR6, AMD RDNA 4, AI-Accelerators, DisplayPort 2.1a, PCIe 5.0, Blower Cooler

• Professional AI & Creator Workstation: AMD Radeon AI PRO R9700 GPU with 32GB GDDR6 is engineered for AI development, professional content creation, and compute-intensive workloads.
• Massive 32GB Memory Capacity: 32GB of GDDR6 memory on a 256-bit bus provides ample bandwidth for large AI models, 8K video editing, and complex 3D rendering.
• Advanced RDNA 4 with AI Accelerators: 64 Compute Units with 3rd Gen Ray Tracing and dedicated 2nd Gen AI Accelerators for groundbreaking AI performance and visual computing.
• Professional Blower Cooling: Efficient single blower design exhausts heat directly out of the chassis, ideal for multi-GPU workstation and server configurations.
• Enterprise-Grade Thermal Solution: Vapor chamber heatsink with industrial Honeywell PTM7950 thermal interface material ensures reliable cooling under sustained professional loads.

Buy on Amazon

This is a model request setting, not a switch that turns thinking on or off. Choose among the documented effort levels according to the needs of your application, and confirm the exact placement and supported options in the API reference for the endpoint you use. The available evidence does not establish a specific latency, quality, or cost difference for each effort value, so do not assume one without checking current Moonshot documentation.

What is the difference between K3.1 Pro and K3.1 Pro Highspeed?

They are separate model IDs: kimi-k3.1-pro is the standard flagship, while kimi-k3.1-pro-highspeed is the faster variant. Moonshot describes Highspeed as roughly 2–3× faster while retaining the same capabilities.

The speed figure is Moonshot’s description; no independent timing test or conditions are established here. If response speed is central to your application, compare the variants under your own workload and verify their current availability and prices in the model catalog before routing production traffic.

How much does Kimi K3.1 Pro cost?

Moonshot AI’s 2026 model catalog lists K3.1 Pro at $2 per million input tokens and $10 per million output tokens. Those are token rates, not a flat subscription price. A request that both supplies input and generates output can incur both kinds of usage charges.

Rank #4

Sale

Apple 2026 MacBook Pro Laptop with Apple M5 Max chip with 18-core CPU and 40-core GPU: Built for AI, 16.2-inch Liquid Retina XDR Display, 48GB Unified Memory, 2TB SSD, Wi-Fi 7; Silver

• FAST RUNS IN THE FAMILY — The 16-inch MacBook Pro with the M5 Pro or M5 Max chip brings next-generation speed and powerful on-device AI to personal, professional, and creative tasks. With all-day battery life, double the starting storage,* and a breathtaking Liquid Retina XDR display, it’s pro in every way.*
• BUCKLE UP — Along with a next-generation CPU, faster unified memory, and up to 2x faster SSD storage,* M5 Pro and M5 Max feature a more powerful GPU with a Neural Accelerator built into each core, delivering faster AI performance and on-device training capabilities. So you can blaze through demanding workloads at mind-bending speeds.
• BUILT FOR AI — Apple silicon, and every major component that powers it, is designed to run demanding on-device AI workloads like LLM inference and training. And Apple Intelligence helps you write, express yourself, and get things done effortlessly with groundbreaking privacy protections at every step.*
• ALL-DAY BATTERY LIFE — MacBook Pro delivers the same exceptional performance whether it’s running on battery or plugged in.*
• MACOS RUNS APPS FAST — All your go-to apps run lightning fast in macOS, including built-in apps like FaceTime and Messages. Plus, built-in virus protection and free software updates help keep your Mac running smoothly and securely.

$4,499.00

Buy on Amazon

Separately, Moonshot requires a successful top-up of at least $1 to unlock K3.1 Pro. The account’s cumulative top-up also determines its tier and affects concurrency and RPM, TPM, and TPD limits. The listed token prices and access requirement are distinct: topping up unlocks access, while usage is billed according to applicable token rates. Prices, limits, and access requirements can change, so confirm the current catalog and account limits before budgeting or launching a service.

Should I use Moonshot directly or a managed gateway?

Direct Moonshot access keeps the API account and direct model access with Moonshot. A managed gateway can add another provider layer and operational controls, but its account, billing, privacy, availability, and routing terms must be assessed separately.

Vercel announced Kimi K3.1 Pro and Highspeed support in AI Gateway on 23 October 2026. Its announcement describes support for AI SDK, Chat Completions, Responses, Anthropic Messages, and coding-agent integrations, along with usage tracking, budgets, routing rules, retries and failover, and bring-your-own-key (BYOK). Vercel says there is no platform fee on inference. These are Vercel’s announced gateway capabilities, not Moonshot account terms.

Choose direct access when you want the documented Moonshot API path and account relationship. Consider a gateway if its additional routing or observability features solve a real operational need, but first verify who handles billing, what data terms apply, whether the model is available in your region, and how the gateway’s costs compare with direct token rates.

Best Value

MINISFORUM MS-S1 MAX Mini AI Workstation PC, AMD Ryzen AI Max+ 395 (16C/32T),RDNA3.5 GPU,128GB LPDDR5x RAM 2TB SSMINI PC, Dual M.2 PCIe 4.0,PCIe x16 Slot, USB4 V2(80Gbps)& Dual 10GbE, 320W PSU,Wi-Fi 7

• 【High-Performance APU】The MS-S1 MAX features an AMD Ryzen AI Max+ 395 APU, integrating a Zen 5 architecture CPU (up to 5.1GHz, 16C/32T, 64M L3 Cache), an RDNA 3.5 GPU, and an NPU (50 TOPS). The total system output is 126 TOPS. It provides powerful parallel computing capabilities for demanding AI workflows. It is ideal for running local LLMs, multimodal models, and computationally intensive tasks
• 【LPDDR5x-8000MT/s Unified Memory】Equipped with 128GB of LPDDR5x-8000MT/s unified memory,4TB pcle SSD,it enables the CPU and GPU to access a shared, high-bandwidth memory pool with extremely low latency. This architecture eliminates traditional VRAM bottlenecks, ensuring smoother data transfer during high-intensity computations and maximizing performance stability under heavy loads. It is ideal for large-scale AI inference, 3D workloads, and complex timelines in video editing.
• 【Flexible Expansion】The MS-S1 MAX features USB4 V2 (up to 80Gbps), dual 10GbE LAN, HDMI 2.1 (up to 8K60), a full-length PCIe x16 expansion slot, and dual M.2 slots supporting up to 16TB RAID 0/1. Wi-Fi 7 provides stronger signal coverage and a more stable wireless experience. The slide-out design facilitates upgrades and maintenance. It easily adapts to personal, studio, or rack-mount enterprise environments
• 【High-Efficiency Cooling System】Utilizing an aerospace-grade aluminum alloy chassis, copper base plate, six heat pipes, dual turbine fans, and advanced PCM thermal conductive material, it maintains stable cooling performance even under continuous load. This system supports 130W continuous power and 160W peak power operation, with a built-in 320W power supply. It boasts multiple global certifications including CCC, FCC, UL, CE, and UKCA, ensuring stable and reliable operation in various environments
• 【Cluster Design】Two MS-S1 MAX units can be configured as a dual-unit cluster to run a large 235B Q4 model locally, achieving an output speed of 10.87 tok/s. Supporting 2U rack deployment, multiple MS-S1 MAX units can be cascaded into a distributed cluster to create a high-efficiency AI computing center. A cluster of four MS-S1 MAX units successfully ran a DeepSeek-R1 671B Q4 large model. A reserved cluster power-on interface allows for unified start-up and shutdown

$3,919.00

Buy on Amazon

What should I check if a request fails?

Start with the account, key, endpoint, and model ID. These are the setup details that determine whether the request is directed and authenticated as intended.

• Model unavailable: Confirm that a successful top-up of at least $1 has been completed and that the account has access to K3.1 Pro.
• Authentication failure: Check that the environment variable is present, that the request sends it as a Bearer key, and that the key was copied correctly when created. Create or rotate a key through the platform if needed; do not paste secrets into client code or public logs.
• Wrong route or model: For the documented OpenAI-compatible Chat Completions request, confirm the base URL is https://api.moonshot.ai/v1, the route is /chat/completions, and the model is spelled kimi-k3.1-pro or kimi-k3.1-pro-highspeed.
• Capacity or rate constraints: Check the account’s tier and current concurrency, RPM, TPM, and TPD limits. Moonshot ties these limits to cumulative top-up; the exact limits are account-specific and are not specified here.
• Image input not handled as expected: Ensure the request represents vision input as structured content with image parts rather than as a serialized string.
• Unexpected charge estimate: Separate input and output token usage, then check current cache rates and the current model catalog instead of treating the minimum top-up as a per-request price.

For any error that persists, use Moonshot’s current API documentation and account dashboard to verify the exact request format, model availability, and account-specific limits. The details above identify the common configuration checks but do not substitute for the platform’s live error message or current API reference.

Frequently Asked Questions

Can I use Kimi K3.1 Pro for free?

The documented access condition is a successful top-up of at least $1, and the model catalog lists per-token usage prices. A separate free K3.1 Pro quota is not established by the available Moonshot details, so check the current platform for any trial or promotional allowance.

Does Moonshot say whether Kimi API prompts are retained or used for training?

The access and model details summarized here do not establish Moonshot’s data-retention or training-use policy. Review Moonshot’s current privacy and API terms before sending sensitive, regulated, or confidential information.

Is Kimi K3.1 Pro available in my country?

Regional availability is not specified in the documented access details here. Confirm eligibility and service availability in Moonshot’s current platform terms for your location before building around the API.

Can I call Kimi K3.1 Pro from a browser app?

A browser application should not contain a secret API key: Moonshot instructs users not to hard-code or share keys. Put the API call behind a server you control, or use a managed integration only after checking its key-handling, billing, and privacy terms.

Quick Recap

Bestseller No. 1

MINISFORUM MS-02 Ultra Workstation Mini PC, Intel Core Ultra 9 285HX (24C/24T, up to 5.5GHz), PCIe 5.0 x16, 32GB RAM 1TB SSD,USB4 v2 80Gbps, Dual 25GbE+10GbE+2.5GbE, Wi-Fi 7, 350W PSU

$1,659.00

Bestseller No. 2

AI WORKSTATION GUIDE: A Practical Handbook for Developers, Data Scientists And Home AI Lab Builders on Hardware Selection, GPU Setup, LLM Deployment And Performance Optimization

$33.69

Bestseller No. 3

ASRock Radeon AI PRO R9700 Creator 32GB Professional Graphics Card, 2920 MHz Boost Clock, GDDR6, AMD RDNA 4, AI-Accelerators, DisplayPort 2.1a, PCIe 5.0, Blower Cooler

SaleBestseller No. 4

Apple 2026 MacBook Pro Laptop with Apple M5 Max chip with 18-core CPU and 40-core GPU: Built for AI, 16.2-inch Liquid Retina XDR Display, 48GB Unified Memory, 2TB SSD, Wi-Fi 7; Silver

$4,499.00

Bestseller No. 5

MINISFORUM MS-S1 MAX Mini AI Workstation PC, AMD Ryzen AI Max+ 395 (16C/32T),RDNA3.5 GPU,128GB LPDDR5x RAM 2TB SSMINI PC, Dual M.2 PCIe 4.0,PCIe x16 Slot, USB4 V2(80Gbps)& Dual 10GbE, 320W PSU,Wi-Fi 7

$3,919.00

Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.

AI APIsAPI guideKimi K3.1 ProMoonshot AIPython