Models
Price comparison

Kimi K3

Kimi K3 by Moonshot AI: 17 offers. From €1.65 per 1M input tokens, with EU processing from €2.68.

Calculate costs for this modelCompare offersView price history

Profile

Profile
DeveloperMoonshot AI
TypeLanguage models
OriginCN
Input typestext+bild+video
Context (tokens)1,048,576
Max. output (tokens)943,718
Reasoningohne
Parameters (bn)2,779.93
Open weights✓ yes
Licenceeigene Lizenz
VRAM at 4-bit (GB)1,533 (Rechenzentrum)
Released1 Jul 2026

searchit Entity Extraction (24 Sept 2026): 62.9 %

Offers with processing in the EU (7)

ProviderCountryVariantInputOutputSourceAs of
LyceumDEstandard€2.68€13.41lyceum.technology13 Oct 2026
Nebius Token FactoryNLstandard€2.68€13.41tokenfactory.nebius.com14 Oct 2026
cortecsATstandard€2.69€13.46api.cortecs.ai14 Oct 2026
MeliousDEstandard€2.85€14.25melious.ai13 Oct 2026
Berget AISEstandard€3.00€15.00api.berget.ai14 Oct 2026
GreenPTNLstandard€3.30€16.50docs.greenpt.ai12 Oct 2026
HostYourAINLstandard€3.45€17.25hostyourai.com14 Oct 2026

€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.

Offers outside the EU (10)

ProviderCountryVariantInputOutputSourceAs of
Chutes–standard€1.65€8.49llm.chutes.ai14 Oct 2026
SiliconFlowSGstandard€2.41€12.07www.siliconflow.com2 Oct 2026
DeepInfraUSstandard€2.55€12.74deepinfra.com14 Oct 2026
Novita AIUSstandard€2.68€13.41novita.ai13 Oct 2026
ParasailUSstandard€2.68€13.41www.parasail.io2 Oct 2026
ParasailUSserverless€2.68€13.41www.parasail.io2 Oct 2026
io.netUSstandard€3.22€16.09api.intelligence.io.solutions14 Oct 2026
Venice.aiUSstandard€3.35€16.76docs.venice.ai14 Oct 2026
Venice.aiUSe2ee€3.35€16.76docs.venice.ai14 Oct 2026
Venice.aiUSfast€4.02€20.11docs.venice.ai14 Oct 2026

€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.

AI Act

Whether the developer has signed the Code of Practice for general-purpose AI models: unknown. What this means is explained under “EU and AI Act”. EU processing and AI Act

Benchmarks

Benchmarks
GPQA Diamond (Artificial Analysis)93.5
Humanity's Last Exam (Artificial Analysis)46.9
ARC-AGI-2 (ARC Prize Foundation)60.4
OTIS Mock AIME 2024-2025 (Epoch AI)97.2
FrontierMath Tiers 1-3 v2 (Epoch AI)72.2
SimpleQA Verified (Epoch AI)50.6
LiveBench (Aufgabensatz 2026-01-08)79.19
MMMU-Pro (llm-stats-Abzug, Rang 1..50 von 69)0.82
searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer beziehungen53
searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer entitaeten72.8

Report an error on this page