GLM 5.3
Capabilities
Features
- StreamingSupported
- Function callingSupported
- Structured outputsSupported
- ReasoningSupported
- Context window
- 1M
- Max output
- 128K
- Answered
- 10/10
- Listed
- 8 Oct 2026
- Company
- Z.ai
- Served via
- SaaufAI Cloud
- Upstream API
- OpenAI-compatible
- Model id
- glm-5.3
Disclosures
- 01Are prompts and outputs stored by SaaufAI?No
Whether this gateway keeps the content of requests or responses.
- 02May the upstream provider use data for model training?No
Based on the upstream provider's API terms for this model.
- 03Does the upstream provider retain data for abuse monitoring?Yes
Many providers keep API data for a limited period (often up to 30 days).
- 04Is data processed outside the EU/EEA?Yes
Whether requests may be routed to servers outside the EU/EEA.
- 05Is the model suitable for personal or sensitive data?No
Operator recommendation for sending personal data to this model.
- 06Does the model support image input?Yes
Whether you can send image_url content parts.
- 07Does the model support tool / function calling?Yes
Whether the tools parameter is translated and supported.
- 08Is the model output content-filtered by the provider?No
Whether the upstream provider applies its own safety filters.
- 09Does SaaufAI enforce its own safeguards on this model?LiveYes
Usage limits or content rules checked by SaaufAI before a request reaches the provider. Answered automatically from the live configuration.
Active: prompts screened for cybersecurity, fraud & financial crime, illegal drug production, weapons & explosives, chemical & biological threats, violent extremism, self-harm & suicide, harassment & doxxing, sexual content involving minors, adult sexual content, jailbreaks & prompt injection. Prompts are screened by Gemini 3.5 Flash-Lite, with Gemini 3.1 Flash-Lite as backup; the screening model sees their content.
- 10May requests be answered by a different (fallback) model?LiveNo
If the model fails or a safeguard is reached, the request can be served by another model without the response saying so, possibly at a different provider with different data terms. Answered automatically.
Based on the upstream provider's terms. Yes or No is not a rating. how to read these.