AI modelPremium plan

GLM 5.2

Z.ai's GLM-5.2 via Fireworks: flagship agentic engineering and coding with a 1M-token context window. Adds function calling (not available on GLM-5/5.1). Uses 2 premium requests per send before length multipliers. Does not support web search or image input.

You always get the exact model you pick — we never silently route you to another.

Specifications

IntelligenceHigh
SpeedMedium
Context window1,048,576 tokens
Max output128,000 tokens
Knowledge cutoffNot officially published
Input price$1.40 / 1M tokens
Output price$4.40 / 1M tokens
Request cost2 premium requests
Plan tierPremium
InputText
OutputText
FeaturesCached input: $0.26 / 1M tokens, 2 premium requests per send before length multipliers, Function calling supported, Fine-tuning not supported on Fireworks serverless
Model IDglm-5p2

Related models