Compare AI models

Specifications
Parameters
4B355B
Context window
128k200k
API pricing
Input price
—$0.60
Output price
—$2.20
Cached input price
—$0.11
Cheapest input
—$0.40DeepInfra
Cheapest output
—$1.60DeepInfra
—$174Venice · fp4
Benchmarks
AIME 2025
46.3%93.9%
GPQA Diamond
55.1%81%
Overview
CompanyNVIDIAZ.ai
Release dateMay 20 2025Sep 30 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

GLM-4.6 leads Llama Nemotron Nano 4B v1.1 on 2 of the 2 benchmarks they both report (AIME 2025, GPQA Diamond). Only GLM-4.6 has a verified first-party price for an available API: $0.60 per million input tokens and $2.20 per million output tokens. No currently available pay-as-you-go API rate is tracked for Llama Nemotron Nano 4B v1.1. Llama Nemotron Nano 4B v1.1 shipped 133 days before GLM-4.6, so benchmark comparisons should account for the intervening progress.

Llama Nemotron Nano 4B v1.1 has 4B parameters, while GLM-4.6 has 355B. Context windows are 128k (Llama Nemotron Nano 4B v1.1) vs 200k (GLM-4.6).

On AIME 2025, GLM-4.6 leads at 93.9% vs Llama Nemotron Nano 4B v1.1 at 46.3%. On GPQA Diamond, GLM-4.6 leads at 81% vs Llama Nemotron Nano 4B v1.1 at 55.1%.