Skip to content

Moonshot AI · Chat

Kimi K2

Moonshot AI 🇨🇳ChatKimi familyOpen weights. One of its sources says the weights are publicly available.

Newer version: Kimi K3.1. Our catalogue has no release date for Kimi K3.1. We compared the version names in our catalogue.

From Llmgateway's listing:
Moonshot's Kimi K2 model for general tasks.
llminfo IQ
117.4
Max context
256K
Listings
24

Evidence and sources

International API storefront is Singapore-based; principal operating entity 北京月之暗面科技有限公司 (Beijing).

🤗 moonshotai/Kimi-K2-Instructllminfo IQ 117.4, ranked among chat models. From 30 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 95.1, 95% interval 80–111. From 3 benchmark families across 3 sources. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.How Coding IQ is computedFair value (52.3). Costs per task about what its benchmark results predict. From 2 benchmarks with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 11 Jul 2025 Training-data cutoff, as its sources state it Maker HQ: CN (source)
All rankings: #147 on OpenRouter this week #235 on OpenRouter this month #311 on OpenRouter todaySources: Neosantara Inference data, Models.dev data, AI/ML API data, OpenRouter data docs, LLMGateway data, llminfo researchPrimary data from Neosantara Inference from Models.dev: name, weights availability from AI/ML API: primary mode from OpenRouter: knowledge cutoff from LLMGateway: description from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 3 of the 9 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 9 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

Function callingStructured output

Listings

 Moonshot AIkimi-k2Source: GenAI Prices dataNot published by the provider$0.57$2.30
 Flowdotmoonshotai/kimi-k2:free · freeSource: FlowDot data33K$0.00$0.00
 OpenRoutermoonshotai/kimi-k2:free · freeSource: Helicone Costs dataNot published by the provider$0.00$0.00
 LlmgatewayInference by Nebius AI Studiomoonshotai/Kimi-K2-InstructSource: LLMGateway dataNot published by the provider$0.50$2.40
 Vercel AI Gatewayvercel_ai_gateway/moonshotai/kimi-k2Source: LiteLLM data131K$0.55$2.20
 302aisophnet/Kimi-K2Source: 302.ai data64K$0.57$2.29
 Kilomoonshotai/kimi-k2Sources: Kilo AI Gateway data, Models.dev data131K$0.57$2.30
 Nous Portalmoonshotai/kimi-k2Source: Nous Portal Inference Gateway data131K$0.57$2.30
 Vercelmoonshotai/kimi-k2Sources: Models.dev data, Vercel AI Gateway data131K$0.57$2.30
 Wavespeedmoonshotai/kimi-k2Source: WaveSpeed AI data131K$0.57$2.30
Show all 22 listings

Showing 10 of 22: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Aimlapi, Llmgateway Providers, Qiniu.

2 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Agentic

Gaia2Source: Gaia2 (Meta ARE) data · Sep 2025

Coding

Factuality

Human preference

Multilingual

Safety

Other

Data credits: ACEBench, MIT (licence) · Aider LLM Leaderboards (Aider-AI), Apache-2.0 (licence) · BullshitBench by Peter Gostev, MIT (licence) · FinSearchComp, CC BY 4.0 (licence) · LiveMCPBench leaderboard, ICIP-CAS (Mo et al., 2025). Sheet linked from the Apache-2.0 project README; sheet licence not separately stated. · MineBench, MIT (licence) · Multi-SWE-bench experiments (multi-swe-bench/experiments), Apache-2.0; resolved-rate fractions converted to percentages (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence)

Also known as: kimi-k2-0711, kimi-k2-250711, kimi-k2:latest, moonshotai/kimi-k2, moonshotai/kimi-k2:free, novita/kimi-k2, sophnet/kimi-k2, vercel_ai_gateway/moonshotai/kimi-k2

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works