ReferenceUpdated November 18, 2026

Private AI API glossary

This private AI API glossary defines the 22 terms that decide what an AI API keeps.

ABCDEFGHIJKLMNOPQRSTUVWXYZ
A
Abliteration
Removing a model's refusals by projecting the direction that triggers them out of its weights. Arditi et al., 2024.
Abuse monitoring
Keeping prompts and outputs for a fixed window so a provider can investigate misuse later. More
Application state
Data an API keeps between requests, such as stored responses and files. More
B
Batch API
An endpoint that runs requests later for less, storing your inputs until then. More
C
Context window
How many tokens a model reads in one request, prompt and history included.
Covered Models
Anthropic models, such as Claude Fable 5.2, whose prompts it keeps 30 days. More
D
Data processing addendum
A contract that sets how a provider handles personal data for you. More
Default retention
How long a provider keeps prompts if you change nothing. More
F
Flagged content
Requests a classifier marks as likely policy violations, often kept longer. More
G
Grounding
Letting a model search the web or a map service while it answers. More
H
Human review
People at the provider reading your prompts. More
M
Modified Abuse Monitoring
An OpenAI control that keeps your content out of abuse logs, by approval. More
O
Opt-out
A setting that stops a provider training on your data. More
P
Private Safety Processing
An OpenAI option that writes safety records to the customer's own storage. More
Prompt caching
Reusing a processed prompt prefix to save cost, for minutes to a day.
R
Retention period
The time between a provider receiving your prompt and deleting it. More
S
Stateless API
An endpoint that keeps nothing between calls, so you send the full conversation each time. More
Store parameter
A request field that tells an API whether to keep the response. More
T
Training on customer data
Using your prompts and outputs to train or improve models. More
U
Unpaid Services
Google's term for free use of the Gemini API and AI Studio. More
Usage logs
Records of when you called an API and how much you used. More
Z
Zero data retention
A provider not storing prompts or outputs after it returns the response. More