Compare AI models

Specifications
Parameters
8B355B
Context window
4k200k
API pricing
Input price
—$0.60
Output price
—$2.20
Cached input price
—$0.11
Cheapest input
—$0.32DeepInfra
Cheapest output
—$1.40DeepInfra
—$168DeepInfra · fp4
These models have no shared benchmark scores.
Overview
CompanyNVIDIAZ.ai
Release dateNov 15 2023Dec 22 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Nemotron-3 8B and GLM-4.7 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only GLM-4.7 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 Nemotron-3 8B. Nemotron-3 8B shipped 768 days before GLM-4.7, so benchmark comparisons should account for the intervening progress.

Nemotron-3 8B has 8B parameters, while GLM-4.7 has 355B. Context windows are 4k (Nemotron-3 8B) vs 200k (GLM-4.7).

Direct benchmark comparisons are unavailable — Nemotron-3 8B and GLM-4.7 don't publish scores on any of the same benchmarks.