Models / GLM
- Chat
GLM 5.3
A longer-term GLM family target for the Arnict catalog.
RoadmapRead the API docs
GLM model family
About this model
GLM 5.3 is a longer-term roadmap target. GLM 5.3 Flash is listed separately as a coming-soon model. The lineup is subject to change; a successor may ship in its place.
- Parameters
- —Published total
- Native context
- —Published model-card value
- Output guidance
- —Published guidance
Capabilities
- Chat completionsUse this model with the chat-completions API when it is marked Available.
- Native input modalitiesText input is listed in the published catalog metadata.
Published limits
Published model-card facts, kept separate from live availability.
| Metric | Published value | Note |
|---|---|---|
| Arnict API output limit | Not published | Maximum output accepted by the Arnict API for this model |
| Parameters | Not published by upstream | Upstream model card |
| Context window | Not published by upstream | Upstream model card |
| Output guidance | Not published by upstream | Upstream model card |
| Weights / activations | Not published by upstream | Published format |
No additional architecture details are published upstream.
Use zai/glm-5.3 with an OpenAI-compatible client after this model is enabled.
Related models
Available
GLM
GLM 5.3 Flash
Long-context chat, coding and tool workflows with GLM 5.3 Flash.
$0.125 input / 1M
Coming soon
DeepSeek
DeepSeek V4.1 Flash
Multimodal mixture-of-experts model: 552B backbone parameters, with 8B active during prefill and 16B during decoding.
Published rate pending
Coming soon
Qwen
Qwen 3.6 35B A3B
Vision-language mixture-of-experts model: 35B total, 3B active parameters.
Published rate pending