llm.ing

GLM-4.7-Flash

Zhipu AIopen weightsOpenRouter ↗Hugging Face ↗Artificial Analysis ↗

Budget GLM lane for fast coding help, routing, and everyday automation

Benchmarks

BenchmarkCategoryScoreVariantProvenanceSourceObserved
AA Intelligence Indexintelligence22.9independentaaJul 24, 2026
Design Arena — 3dpreference1180mirroropenrouterJul 24, 2026
Design Arena — codecategoriespreference1210mirroropenrouterJul 24, 2026
Design Arena — datavizpreference1157mirroropenrouterJul 24, 2026
Design Arena — gamedevpreference1193mirroropenrouterJul 23, 2026
Design Arena — svgpreference1087mirroropenrouterJul 24, 2026
Design Arena — uicomponentpreference1248mirroropenrouterJul 24, 2026
Design Arena — websitepreference1221mirroropenrouterJul 23, 2026
Median output speedspeed104 tok/sindependentaaJul 24, 2026
Median time to first tokenspeed1.17sindependentaaJul 24, 2026

Includes index data from Artificial Analysis.

Providers

Live operational stats per hosting endpoint, via OpenRouter.

ProviderQuantContext$/1M in · outUptime 24hLatencyThroughput
Cloudflare131K$0.061 · $0.498.81%
DeepInfrabf16203K$0.06 · $0.498.40%
Novitabf16200K$0.07 · $0.487.90%
Venicefp8128K$0.125 · $0.594.38%