Compare AI models

Specifications
Parameters
1T9B
Context window
256k128k
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · bf16—
Benchmarks
LiveCodeBench
83.1%28.5%
Overview
CompanyMoonshot AIZ.ai
Release dateNov 6 2025Jul 5 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 Thinking leads CodeGeeX4-ALL-9B on 1 of the 1 benchmark they both report (LiveCodeBench). CodeGeeX4-ALL-9B shipped 489 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.

Kimi K2 Thinking has 1T parameters, while CodeGeeX4-ALL-9B has 9B. Context windows are 256k (Kimi K2 Thinking) vs 128k (CodeGeeX4-ALL-9B).

On LiveCodeBench, Kimi K2 Thinking leads at 83.1% vs CodeGeeX4-ALL-9B at 28.5%.