Compare AI models

Specifications
Parameters
1T4B
Context window
256k256k
API pricing
Input price
$0.95—
Output price
$4.00—
Cached input price
$0.16—
Cheapest input
$0.3895Baidu—
Cheapest output
$1.64Baidu—
$160Baidu · fp4—
Benchmarks
GPQA Diamond
90.5%53.2%
Overview
CompanyMoonshot AINVIDIA
Release dateApr 20 2026Mar 16 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2.6 leads Nemotron 3 Nano 4B on 1 of the 1 benchmark they both report (GPQA Diamond). Only Kimi K2.6 has a verified first-party price for an available API: $0.95 per million input tokens and $4.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Nemotron 3 Nano 4B. Nemotron 3 Nano 4B shipped 35 days before Kimi K2.6, so benchmark comparisons should account for the intervening progress.

Kimi K2.6 has 1T parameters, while Nemotron 3 Nano 4B has 4B. Context windows are 256k (Kimi K2.6) vs 256k (Nemotron 3 Nano 4B).

On GPQA Diamond, Kimi K2.6 leads at 90.5% vs Nemotron 3 Nano 4B at 53.2%.