AiCostCompare

Kimi K3 (batch)

by Moonshot AI · moonshotai/kimi-k3:batch · #394 cheapest of 457 paid models

Prices updated Nov 18, 2026, 1:33 PM UTC · refreshed nightly

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$2.28

per 1M tokens

Output

$11.40

per 1M tokens

Blended (3:1)

$4.56

3 input : 1 output

Cache read

$0.228

per 1M cached tokens

Cache write

—

per 1M tokens

Cache & batch economics

Effective prices for Kimi K3 (batch) with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$4.56$0.244—
50%$3.79$0.1414−42%
90%$3.17$0.0593−76%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.00456$4.56
Document summary8,0001,000$0.0296$29.64
Codebase question (RAG)30,0002,000$0.0912$91.20
Long-context analysis150,0005,000$0.399$399.00

Performance

Intelligence Index

17.4

AA composite quality

Coding Index

72

Math Index

—

Agentic Index

29.3

Output speed

—

median

Time to first token

—

median

Time to first answer

—

after reasoning tokens

Design Arena Elo

CategoryElo
Website1,337
Web apps1,277
Full-stack1,289
Mobile apps1,252
Android native1,255
UI components1,340
Data viz1,349
SVG1,296
3D1,365
Game dev1,354
Agentic game dev1,201
Godot game dev1,193
HTML slides1,152
Python→PPTX slides1,223
Code categories1,351
ASCII art1,351
blender3d1,124
codetovideo1,294
pdf1,279
spreadsheet1,052

Specs

Context window

1.05M

tokens

Max output

16K

tokens

Input modalities

text, image, video

Tokenizer

Other