Compare AI models

Specifications
Parameters
2.8T8B
Context window
1M8k
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 2026Aug 21 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K3 and Mistral NeMo Minitron 8B 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 Mistral NeMo Minitron 8B. Mistral NeMo Minitron 8B shipped 694 days before Kimi K3, so benchmark comparisons should account for the intervening progress.

Kimi K3 has 2.8T parameters, while Mistral NeMo Minitron 8B has 8B. Context windows are 1M (Kimi K3) vs 8k (Mistral NeMo Minitron 8B).

Direct benchmark comparisons are unavailable — Kimi K3 and Mistral NeMo Minitron 8B don't publish scores on any of the same benchmarks.