Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | z-aiZ.ai: GLM 4.5Remove × | zai-orgGLM-4.6V-FlashRemove × |
|---|---|---|
| What’s different | GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5… | 131.1K context · Image input · Open weights |
| Date | Jul 20, 2025Listed | Dec 7, 2025Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $0.60 in / $2.20 out/ 1M tokensZ.AI · via OpenRouter · all routes ↗z-ai/fp8 · quantization=fp8 | $0.30 in / $0.90 out/ 1M tokensnovita · via Hugging Face · all routes ↗ |
| Provider endpoints | 3 endpoints → | 2 endpoints → |
Specifications | ||
| Context window | 131.1K | 131.1K |
| Max output | 98.3K | — |
| Parameters | — | — |
| Tool calling | Supported | Supported |
| Structured output | Supported | Not reported |
| Image input | Not reported | Supported |
| Reasoning | Supported | Not reported |
| Prompt caching | Supported | Not reported |
| Open weights | Supported | Supported |