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
| Intelligence | High |
|---|---|
| Speed | Medium |
| Context window | 1,048,576 tokens |
| Max output | 128,000 tokens |
| Knowledge cutoff | Not officially published |
| Input price | $1.40 / 1M tokens |
| Output price | $4.40 / 1M tokens |
| Request cost | 2 premium requests |
| Plan tier | Premium |
| Input | Text |
| Output | Text |
| Features | Cached input: $0.26 / 1M tokens, 2 premium requests per send before length multipliers, Function calling supported, Fine-tuning not supported on Fireworks serverless |
| Model ID | glm-5p2 |