Skip to content

Moonshot AI · Chat

Kimi K2 0905

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.

sophnet's Kimi-K2-0905

llminfo IQ
119.4
Maker's price
$1.075 blended / 1M
Max context
262K
Listings
17

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-Instruct-0905llminfo IQ 119.4, ranked among chat models. From 22 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 92.5, 95% interval 82–103. From 4 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.How Coding IQ is computedGood value (56.6). Cheaper per task than its benchmark results predict. From 3 benchmarks with measured task costs. A fair amount of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTerse (41 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 2,518 output tokens per task at default effort.How the Yap score worksReleased 5 Sep 2025 Training-data cutoff, as its sources state it Maker HQ: CN (source)
All rankings: #279 on OpenRouter this week #280 on OpenRouter today #302 on OpenRouter this monthSources: Novita AI data, Models.dev data, AI/ML API data, OpenRouter data docs, 302.ai data, llminfo researchPrimary data from Novita AI from Models.dev: name, weights availability from AI/ML API: primary mode from OpenRouter: knowledge cutoff from 302.ai: 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. 2 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-k2-0905-previewSource: GenAI Prices data262K$0.60cache read $0.15$2.50——
 Tencent Lkeapkimi-k2-0905-previewSource: Tencent Cloud LKEAP PricingNot published by the provider——
 Flowdotmoonshotai/kimi-k2-0905Source: FlowDot data262K$0.40$2.00——
 302aimoonshotai/kimi-k2-0905Sources: 302.ai data, Models.dev data262K$0.572cache read $0.143$2.286——
 Ppiomoonshotai/kimi-k2-0905Source: PPIO data262K——
 Kilomoonshotai/kimi-k2-0905Sources: Kilo AI Gateway data, Models.dev data262K$0.60$2.50——
 Nous Portalmoonshotai/kimi-k2-0905Source: Nous Portal Inference Gateway data262K$0.60$2.50——
 OpenRouterInference by Novita AImoonshotai/kimi-k2-0905 · fp8Source: OpenRouter data docs262K$0.60$2.5036730.5ms
 Jiekoumoonshotai/kimi-k2-0905Source: Models.dev data262K$0.60$2.50——
 Novita AImoonshotai/kimi-k2-0905Sources: LiteLLM data, Models.dev data, Novita AI data262K$0.60$2.50——
Show all 13 listings

Showing 10 of 13: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Aimlapi, Obscurify.

4 listings without a price are hidden.

Benchmarks

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

Multilingual

Coding

HumanEvalSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Vision

Agentic

Knowledge

MMLUSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MMLU-ProSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Math

MATHSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Human preference

Reasoning

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Other

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · SWE-fficiency (swefficiency.com) leaderboard materials, CC BY 4.0; Human Expert reference row omitted (licence)

Also known as: kimi-k2-0905-preview, moonshotai/kimi-k2-0905, moonshotai/kimi-k2-0905:exacto, novita/moonshotai/kimi-k2-0905, sophnet/kimi-k2-0905

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