Compare AI models

Specifications
Parameters
2.8T8B/43B
Context window
1M4k
API pricing
Input price
$3.00—
Output price
$15.00—
Cached input price
$0.30—
Cheapest input
$0.153Wafer—
Cheapest output
$9.50Chutes—
$535Wafer · mxfp4—
These models have no shared benchmark scores.
Overview
CompanyMoonshot AINVIDIA
Release dateJul 16 2026Mar 21 2023
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Kimi K3 and NeMo GPT (8B/43B) don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Kimi K3 has a verified first-party price for an available API: $3.00 per million input tokens and $15.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for NeMo GPT (8B/43B). NeMo GPT (8B/43B) shipped 1213 days before Kimi K3, so benchmark comparisons should account for the intervening progress.

Kimi K3 has 2.8T parameters, while NeMo GPT (8B/43B) has 8B/43B. Context windows are 1M (Kimi K3) vs 4k (NeMo GPT (8B/43B)). Kimi K3 is open weight, while NeMo GPT (8B/43B) is closed.

Direct benchmark comparisons are unavailable — Kimi K3 and NeMo GPT (8B/43B) don't publish scores on any of the same benchmarks.