Kimi K2 Thinking

Retired May 2026

Reasoning variant of Kimi K2, Moonshot AI's 1T-parameter MoE, designed for deep multi-step reasoning and complex analysis.

Params: 1T, 32B active
Context: 262K tokens
License: Modified MIT

Visit Moonshot AI Compare vs other LLMs →

Hosted API price

Cheapest via Novita · per 1M tokens

USD

Input: $0.60 /1M
Output: $2.50 /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 K2 Thinking, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Kimi K2 Thinking, 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
Novita	$0.60	$2.50	$0.15	$11.00	Visit website
Moonshot AI Creator	Open weights, no hosted price				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.

Estimated cost to self-host

Kimi K2 Thinking needs about 554 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 8× A100 at about $9,850 a month.

That costs the same as roughly 11B tokens a month on Novita's API. Self-hosting is more expensive below that volume.

Single node ≤ 8

What it costs to self-host Kimi K2 Thinking at each precision: the memory it needs, the cheapest rental that holds it, that rental's month and the API volume it pays off at
Precision	Memory	Cheapest fit (32K context)(Full 262K context)	Cost /mo	Break-even vs API
4-bit INT4 / FP4	554 GB570 GB	8× A100	$9,850$9,850	11B tokens /mo11B tokens /mo
8-bit FP8 / INT8	1,003 GB1,011 GB	4× B300	$22,723$22,723	25B tokens /mo25B tokens /mo
16-bit FP16 / BF16	2,004 GB2,020 GB	8× B300	$45,446$45,446	50B tokens /mo50B tokens /mo

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. Pricing methodology.

Similarly priced models

The models nearest Kimi K2 Thinking by blended rate, each at its own cheapest provider.

Models priced nearest Kimi K2 Thinking per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Kimi K2 Thinking
Qwen3.5-Plus Alibaba Cloud	$0.7333	$0.40	$2.40	1M		−20%
GLM-5 Z.AI	$0.7667	$0.60	$1.60	200K		−16%
DeepSeek R1 Distill Llama 70B DeepSeek	$0.80	$0.80	$0.80	131K		−13%
GLM-4.7 Z.AI	$0.8667	$0.60	$2.20	205K		−5%
Gemini 3 Flash Preview Google Cloud	$0.9167	$0.50	$3.00	1M	Jan 2025	0%
Kimi K2 Thinking This model Moonshot AI	$0.9167	$0.60	$2.50	262K
Qwen3.6-Plus Alibaba Cloud	$0.9167	$0.50	$3.00	1M		0%
GLM-5.2 Z.AI	$0.95	$0.70	$2.20	1M		+4%
Nemotron 3 Ultra 550B A55B Nvidia	$0.99	$0.66	$2.64	1M	Sep 2025	+8%
DeepSeek R1 DeepSeek	$1.00	$0.70	$2.50	128K		+9%
DeepSeek R1 Turbo DeepSeek	$1.00	$0.70	$2.50	64K		+9%

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.

Runpod

Spin Up a GPU in Seconds - No Setup Required

Deploy AI Models Globally in 30+ Regions

Scale from 0 to 1000 GPUs on Demand

PyTorch, Tensorflow & Docker Ready

Learn more

Capabilities

What Kimi K2 Thinking accepts and can do, as published by Moonshot AI.

Text Accepts and generates natural-language text.
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.

Common questions

What is Kimi K2 Thinking good for?

Multi-step reasoning and long tool-calling chains: Moonshot built it as a thinking agent that mixes chain-of-thought with tool calls. Modified MIT weights allow self-hosting, on a multi-GPU node.

When is Kimi K2 Thinking not a good fit?

New deployments: Moonshot retired it in May 2026, and the later Kimi models carry the line on. Text only, and running the weights yourself takes a multi-GPU node.

What is the cheapest way to run Kimi K2 Thinking?

Hosted, unless you push serious volume. Novita charges $0.60 in / $2.50 out per 1M tokens. The cheapest rental that fits is 8x A100 at $9,850 a month, which costs the same as about 11B tokens a month on that API.

Can I self-host Kimi K2 Thinking?

Yes. The weights are Modified MIT licensed. At 4-bit it needs about 554 GB of GPU memory, which starts at roughly $9,850 a month on the cheapest rental that fits.