OpenRating is an independent, open-source AI rating platform. Join the community

OOpenRating
All models

Moonshot AI · Released May 20, 2026

Kimi K3 (max)

Moonshot AI's frontier open-weights reasoning model with explicit multi-step thinking traces and deep STEM problem solving.

Open weights

OpenRating Index

59.8

0–100 composite

Reasoning Index

85.5

0–100 composite

Cost / Task

$0.84

benchmark run

Output speed

38 tok/s

blended tok/s

Time to first token

1.3s

median latency

Input price

$0.9

per 1M tokens

Output price

$3.6

per 1M tokens

Context window

256K

tokens

Strengths

  • Explicit chain-of-thought output with granular reasoning

  • Open weights suitable for custom inference deployment

  • Exceptional long-form synthesis and bilingual mastery

How we rate Kimi K3 (max)

OpenRating scores every model on the same axes. The OpenRating Index is a weighted composite of reasoning, knowledge, and agentic benchmarks, normalised to a 0–100 scale. Speed is blended output measured in tokens per second under standardised load, with time-to-first-token reported separately. Prices are list input and output prices per million tokens, and Task Cost measures end-to-end workload spending.

OpenRating Index

59.8

Reasoning Index

85.5

Token Pricing

Input per 1M tokens

$0.9

Output per 1M tokens

$3.6

Cost of 1M input + 1M output

$4.5

Task Cost Economics

Empirical cost breakdown for a standard OpenRating Index benchmark task ($0.84 total).

Reasoning (Chain of Thought)
$0.28
Answer generation
$0.10
Cache write overhead
$0.18
Cache hit queries
$0.25
Input payload
$0.019