GLM 5.3 Flash

by Z.aivia SaaufAI Cloud

Compare

Speed

Not measured yet

Measured from real traffic once there is enough

Input

Text, Image

Output

Text

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-flash

Disclosures

6 yes4 no0 open

01
Are prompts and outputs stored by SaaufAI?
Whether this gateway keeps the content of requests or responses.
No
02
May the upstream provider use data for model training?
Based on the upstream provider's API terms for this model.
Yes
03
Does the upstream provider retain data for abuse monitoring?
Many providers keep API data for a limited period (often up to 30 days).
Yes
04
Is data processed outside the EU/EEA?
Whether requests may be routed to servers outside the EU/EEA.
Yes
05
Is the model suitable for personal or sensitive data?
Operator recommendation for sending personal data to this model.
No
06
Does the model support image input?
Whether you can send image_url content parts.
Yes
07
Does the model support tool / function calling?
Whether the tools parameter is translated and supported.
Yes
08
Is the model output content-filtered by the provider?
Whether the upstream provider applies its own safety filters.
No
09
Does SaaufAI enforce its own safeguards on this model?Live
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.
Yes
10
May requests be answered by a different (fallback) model?Live
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.
No

Based on the upstream provider's terms. Yes or No is not a rating. how to read these.

Capabilities

Features

Disclosures