Kimi K3.1 Pro

Moonshot AI's flagship and the first of its K3.1 series: Kimi K3 post-trained with far more reinforcement learning compute, aimed at long-horizon coding and knowledge work.

Context: 1M tokens
Released: Oct 2026

Visit Moonshot AI Compare vs other LLMs →

Hosted API price

List price via Moonshot AI · per 1M tokens

USD

Input: $2.00 /1M
Output: $10.00 /1M
Hosted by: 2 providers

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving Kimi K3.1 Pro, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Kimi K3.1 Pro, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cached input /1M	Cost at 10M in + 2M out	Link
Moonshot AI Creator	$2.00	$10.00	$0.20	$40.00	Visit website
Novita	$2.00	$10.00	$0.20	$40.00	Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Similarly priced models

The models nearest Kimi K3.1 Pro by blended rate, each at its own cheapest provider.

Models priced nearest Kimi K3.1 Pro per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Kimi K3.1 Pro
Claude Sonnet 5.5 Anthropic	$3.3333	$2.00	$10.00	1M	Jun 2026	0%
Gemini 4 Argon Google Cloud	$3.3333	$2.00	$10.00	1M	Mar 2026	0%
GPT-5.6 Sol OpenAI	$3.3333	$2.00	$10.00	1M	Feb 2026	0%
GPT-6 Sol OpenAI	$3.3333	$2.00	$10.00	1M	Apr 2026	0%
GPT-6.1 Sol OpenAI	$3.3333	$2.00	$10.00	1M	Apr 2026	0%
Kimi K3.1 Pro This model Moonshot AI	$3.3333	$2.00	$10.00	1M
Gemini 3.1 Pro Preview Google Cloud	$3.6667	$2.00	$12.00	1M	Jan 2025	+10%
GPT-5.6 Terra OpenAI	$3.6667	$2.00	$12.00	1M	Feb 2026	+10%
Kimi K3 Moonshot AI	$3.6667	$2.00	$12.00	1M		+10%
Command A Cohere	$3.75	$2.50	$10.00	256K		+13%
Command R+ 08-2024 Cohere	$3.75	$2.50	$10.00	128K	Feb 2023	+13%

USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Thunder Compute

RTX A6000 from $0.35, A100 from $1.09, per GPU per hour

Billed per minute, no commitment, no minimums

One click into VS Code or Cursor, no SSH setup

See live pricing

Capabilities

What Kimi K3.1 Pro accepts and can do, as published by Moonshot AI.

Text Accepts and generates natural-language text.
Image Accepts images as input alongside text.
Video Accepts video as input.
Reasoning Thinks before it answers, always on or as a switchable mode.
Function calling Connect to external tools, APIs, and systems.
Structured output Return responses in structured formats like JSON.
Web search Search the web for up-to-date information.
File upload Process uploaded documents, spreadsheets, and other files.

Common questions

What is Kimi K3.1 Pro good for?

Long coding sessions, 3D modeling and game builds in tools such as Blender and Unreal Engine, and financial research and modeling, where Moonshot reports its main gains over K3. It takes images and video as well as text.

When is Kimi K3.1 Pro not a good fit?

Self-hosting for now: Moonshot has promised the weights but not yet published them or their license, and a model of K3's size takes more than one node. No audio input, thinking cannot be switched off, and no maximum output is published.

What is the cheapest way to run Kimi K3.1 Pro?

The cheapest hosted rate is $2.00 / $10.00 per 1M tokens via Moonshot AI.

How does Kimi K3.1 Pro compare with Kimi K3?

Moonshot says K3.1 Pro is Kimi K3 post-trained with substantially more reinforcement learning compute, with gains across coding, 3D creation and financial research, and fewer factual errors on hard real-world prompts. Same 1M-token context and text, image and video input. Kimi K3.1 Pro lists at 33% less per 1M input tokens and 33% less per 1M output tokens than Kimi K3. It keeps its weights closed, where Kimi K3 publishes them under Kimi K3 License.

Can I self-host Kimi K3.1 Pro?

No. Moonshot AI does not publish the weights; Kimi K3.1 Pro is available only through hosted APIs.