Skip to main content

Engineering ready

GLM-5.3-Flash FP8 Production Package

GLM / GLM-5.3-Flash · fp8 · Engineering status: Engineering ready

Details

Transformation lineage

Base releaseGLM-5.3-Flash
Model engineeringFP8 Quantization, Runtime packaging, Evaluation and benchmarking
Delivery optionsDownload package / Host with FusionPointAI / Download + host

Transparent pricing

  • Base model engineeringUSD 95,700
  • FP8 QuantizationUSD 5,900
  • Runtime packagingUSD 2,800
  • Evaluation and benchmarkingUSD 3,600
  • Download packageUSD 1,500
  • Managed deployment setupUSD 3,200
  • One-time engineeringUSD 112,700

Monthly hosting

  • 3 x NVIDIA H200 SXM 141GBUSD 7,035
  • Monthly hostingUSD 7,035