Compare AI models

Specifications
Parameters
—30B
Context window
400k200k
API pricing
Input price
$0.05$0.00
Output price
$0.40$0.00
Cached input price
$0.005$0.00
Cheapest input
$0.025OpenAI—
Cheapest output
$0.20OpenAI—
$30.00OpenAI list price$0.00Z.ai list price
Benchmarks
SWE-Bench Verified
54.7%59.2%
AIME 2025
85.2%91.6%
Overview
CompanyOpenAIZ.ai
Release dateAug 7 2025Jan 19 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GLM-4.7-Flash leads GPT-5 nano on 2 of the 2 benchmarks they both report (SWE-Bench Verified, AIME 2025). GLM-4.7-Flash is cheaper on both input and output: $0.00 vs $0.05 per million input tokens, and $0.00 vs $0.40 per million output tokens. GPT-5 nano shipped 165 days before GLM-4.7-Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 400k (GPT-5 nano) vs 200k (GLM-4.7-Flash). GPT-5 nano is closed, while GLM-4.7-Flash is open weight.

On SWE-Bench Verified, GLM-4.7-Flash leads at 59.2% vs GPT-5 nano at 54.7%. On AIME 2025, GLM-4.7-Flash leads at 91.6% vs GPT-5 nano at 85.2%.