Kimi K3 Fast is Moonshot AI (Kimi)'s language model with a 1.0M context window and up to 131K output tokens, starting at $4.50 / 1M input and $22.50 / 1M output. A fast-inference variant of Kimi K3 supporting long-horizon coding, reasoning, and knowledge work with a 1M-token context window.
Specifications
Canonical IDmoonshot-kimi-k3-fast
TypeLanguage
StatusActive
CreatorMoonshot AI (Kimi)Moonshot AI (Kimi)
Providers
Context Window1.0M tokens
Max Output131K tokens
Input ModalitiesImagePDF
Output ModalitiesText
Reasoning Effortsdefault
Release Date · 16 days ago

Capabilities

Input2/5
Text·
Image
Audio·
Video·
PDF
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities3/13
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
Vercel AI Gateway logo
Vercel AI Gateway
moonshotai/kimi-k3-fast
$4.50$22.50$0.45

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Kimi K3 Fast1.0M$4.50$22.50Current
Kimi K31.0M$3.00$15.00Available
Kimi K2.7 Code High Speed262K$1.90$8.00Available
Kimi K2.7 Code262K$0.475$2.00Available
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

Model IDs

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