About GLM 5.3 Flash
GLM-5.3-Flash is a native multimodal model from Z AI built for efficient coding and long-horizon agent tasks. With 320 billion total parameters and just 18 billion active, it outperforms GLM-5.2 across benchmarks at a fraction of the cost while approaching Claude Opus 4.8 on coding and agentic tasks.
It is the first multimodal model in the GLM-5 series, combining sparse and linear attention in a hybrid architecture that cuts long-context serving costs. Reasoning is always on and cannot be disabled; the reasoning_effort parameter accepts low, high, and max, with max as the default. Weights are published under an MIT license.
Fine-tuning trains an adapter over attention while the routed experts stay frozen in 4 bits, so a fine tune of this model costs about what a far smaller one would.
| Metric | Value |
|---|---|
| Parameter Count | 320 billion |
| Active Parameter Count | 18 billion |
| Mixture of Experts | Yes |
| Context Length | 1,048,576 tokens |
| Max Output | 131,072 tokens |
| Multilingual | Yes |
| Tool Use | Yes |
| Structured Outputs | Yes |
Ready to build with GLM 5.3 Flash?
Try GLM 5.3 Flash in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "zai-org-glm-5-3-flash",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'