GLM-5.3
Open weightsRelease date unknown
- Context
- 1.05M tokens
- Max output
- —
- Input / 1M
- —
- Output / 1M
- —
0 mapped APIs
Model Family
GLM-5.3
GLM-5.3 is Z.ai's current open-weight GLM generation for coding, reasoning, long-horizon agentic tasks, and efficient multimodal inference.
Official documentationVerified Oct 5, 2026
Models
2
Provider
Z.ai
API access
—
Context range
1.05M tokens
Input price range
—
Output price range
—
Overview
The Open Models pilot represents the generation with GLM-5.3 and GLM-5.3-Flash. The flagship continues the large MoE line, while Flash uses a newly trained base model with a hybrid sparse-and-linear-attention architecture.
Models in this family
Current indexed models and their documented specifications.
GLM-5.3-Flash
Open weightsRelease date unknown
- Context
- 1.05M tokens
- Max output
- —
- Input / 1M
- —
- Output / 1M
- —
0 mapped APIs
| Model | Released | Context | Max output | Input | Output | API |
|---|---|---|---|---|---|---|
| GLM-5.3 Open weights | — | 1.05M tokens | — | — | — | — |
| GLM-5.3-Flash Open weights | — | 1.05M tokens | — | — | — | — |