Kimi K3 is Moonshot AI (Kimi)'s language model with a 1.0M context window and up to 131K output tokens, available from 2 providers, starting at $3.00 / 1M input and $15.00 / 1M output. A flagship reasoning-capable multimodal LLM with 2.8 trillion parameters, built on Kimi Delta Attention (a hybrid linear attention mechanism) with native visual understanding and tool-use support.
Specifications
Canonical IDmoonshot-kimi-k3
TypeLanguage
StatusActive
CreatorMoonshot AI (Kimi)Moonshot AI (Kimi)
Providers
Context Window1.0M tokens
Max Output131K tokens
Input ModalitiesImagePDFText
Output ModalitiesText
Reasoning Effortsdefault
Release Date · 2 days ago
Benchmarks
Intelligence Index
Coding Index
GPQA
0.9
#3
HLE
0.4
#6
Time to First Token
1.35s
#407
SciCode
0.6
#3
LCR
0.7
#4
Output TPS
58.5
#188

Capabilities

Input3/5
Text
Image
Audio·
Video·
PDF
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning
Adaptive Reasoning·
Function Calling
Parallel Function Calling·
Structured Outputs
Native JSON Schema
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
OpenRouter logo
OpenRouter
moonshotai/kimi-k3
$3.00$15.00$0.3
Vercel AI Gateway logo
Vercel AI Gateway
moonshotai/kimi-k3
$3.00$15.00$0.3

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Kimi K31.0M$3.00$15.00Current
Kimi K2.7 Code High Speed262K$1.90$8.00Available
Kimi K2 Thinking Turbo262K$1.15$8.00Deprecated
Kimi K2 Turbo256KAvailable
Kimi K2.5 Non-ReasoningAvailable
Kimi K2 Instruct V0Available
Kimi K2 Preview262K$0.600$2.50Deprecated
Kimi K2 Turbo Preview262K$1.15$8.00Deprecated
Kimi K2.5 Thinking$0.600$3.00Available
Kimi K2.6 Fast262K$2.00$8.00Available
Kimi K2.6 Thinking$0.950$4.00Available

Model IDs

kimi-k3
moonshot-kimi-k3
moonshotai/kimi-k3