Kimi K2

Retired May 2026

Moonshot AI's 1T-parameter MoE model with 32B active, released July 2025 and pre-trained on 15.5T tokens, with enhanced agentic coding in the 0905 update.

Params: 1T, 32B active
Context: 262K tokens
Released: Jul 2025
License: Modified MIT

Visit Moonshot AI Compare vs other LLMs →

Hosted API price

Cheapest via Novita · per 1M tokens

USD

Input: $0.57 /1M
Output: $2.30 /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, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Kimi K2, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cost at 10M in + 2M out	Link
Novita	$0.57	$2.30	$10.30	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 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 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	26B tokens /mo26B tokens /mo
16-bit FP16 / BF16	2,004 GB2,020 GB	8× B300	$45,446$45,446	53B tokens /mo53B 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 by blended rate, each at its own cheapest provider.

Models priced nearest Kimi K2 per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Kimi K2
GPT-3.5 Turbo OpenAI	$0.6667	$0.50	$1.50	16K	Sep 2021	−22%
Mistral Large 3 Mistral	$0.6667	$0.50	$1.50	256K		−22%
Qwen3.5-Plus Alibaba Cloud	$0.7333	$0.40	$2.40	1M		−15%
GLM-5 Z.AI	$0.7667	$0.60	$1.60	200K		−11%
DeepSeek R1 Distill Llama 70B DeepSeek	$0.80	$0.80	$0.80	131K		−7%
Kimi K2 This model Moonshot AI	$0.8583	$0.57	$2.30	262K
GLM-4.7 Z.AI	$0.8667	$0.60	$2.20	205K		+1%
Gemini 3 Flash Preview Google Cloud	$0.9167	$0.50	$3.00	1M	Jan 2025	+7%
Qwen3.6-Plus Alibaba Cloud	$0.9167	$0.50	$3.00	1M		+7%
GLM-5.2 Z.AI	$0.95	$0.70	$2.20	1M		+11%
Nemotron 3 Ultra 550B A55B Nvidia	$0.99	$0.66	$2.64	1M	Sep 2025	+15%

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.

Packet·ai

B200 @ $3.75/h on demand

No contract, no spot interrupts, no cluster minimums

Full root SSH, web dashboard, CI/CD ready

Reserve Now

Capabilities

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

Text Accepts and generates natural-language text.
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 good for?

Agent coding and tool-driven work, which Moonshot aimed the 0905 update at. Its Modified MIT weights allow commercial self-hosting, on a multi-GPU node.

When is Kimi K2 not a good fit?

New deployments: Moonshot retired it in May 2026 and Kimi K2.5 carries the line on. Text only, and running it yourself takes a multi-GPU node.

What is the cheapest way to run Kimi K2?

Hosted, unless you push serious volume. Novita charges $0.57 in / $2.30 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.

How does Kimi K2 compare with Kimi K2.5?

Moonshot built Kimi K2.5 by continuing pretraining on the Kimi K2 base with mixed image and text tokens, which adds vision input, instant and thinking modes, and a swarm mode that splits a task across many sub-agents. Same 262K-token context. Kimi K2 costs 43% more per 1M input tokens and 12% less per 1M output tokens than Kimi K2.5, at each model's cheapest listed provider. It came out 6 months earlier and takes no image and video input, which Kimi K2.5 does.

Can I self-host Kimi K2?

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.