GLM 5.2 — Specifications
| Sviluppatore | Zhipu AI |
|---|
| Tipo | LLM (coding/agentic, MoE) |
|---|
| Modalità | Text → Text |
|---|
| Parametri | 744B total / ~40B active (MoE) |
|---|
| Finestra contestuale | 1M |
|---|
| Output massimo | 131K |
|---|
| Licenza | MIT (open) |
|---|
| Pesi aperti | ✅ Yes |
|---|
| Rilasciato | 2026-06 |
|---|
| Input price | $1.4 /1M |
|---|
| Output price | $4.4 /1M |
|---|
| API providers | Zhipu (Z.ai), OpenRouter |
|---|
🖥️ Run it locally
| VRAM (4-bit) | ~370 GB |
|---|
| Minimum GPU | Multi-GPU server (e.g. 5× H100 80GB) |
|---|
Official page →
Zhipu AI’s open 1M-context model — a 744-billion-parameter mixture-of-experts (≈40B active) using a new ‘IndexShare’ sparse-attention design, notably trained entirely on Huawei chips. MIT open weights; strong on coding, design and agentic tasks.
