Skip to content
OneAtlas

Kimi K2.8 Preview

moonshotai/kimi-k2.8-preview
Moonshot AITextClosed weightsReasoningTool call
Compare 2 providers

Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code

Context

1.05M

1,048,576 tokens

Max output

33K

32,768 tokens

Input

Free

per 1M tokens

Output

Free

per 1M tokens

Providers

2

2 listings

Intelligence

—

Not yet scored

Pricing

USD per 1M tokens · listed by Kimi For Coding (kimi.com)

Token typeStandard
InputFree
OutputFree
Cache readFree
Cache writeFree

Lowest input price across providers: Free.

Capabilities

ReasoningYes

Effort: none, low, high, max

Tool callYes
Structured outputUnknown
TemperatureNo
AttachmentsYes
Interleaved reasoningYes

Field: reasoning_content

Open weightsNo
ModeratedUnknown

Input

TextImageVideo

Output

Text

Benchmarks

Published scores and Design Arena Elo

No published benchmark scores for this model yet.

Rankings

Position on each OneAtlas leaderboard

Providers · 2

2 listings

ProviderModel IDContextInput limitOutputInput $Output $Reasoning $Cache readCache writeAudio inAudio outReasoningToolsStructuredTemp.Updated
Kimi For Coding (kimi.ai)kimi-for-coding1.05M—33KFreeFree—FreeFree——YesYesUnknownNoSep 11, 2026
Kimi For Coding (kimi.com)kimi-for-coding1.05M—33KFreeFree—FreeFree——YesYesUnknownNoSep 11, 2026