Skip to content

[AI Endpoints] - Features & Limitations guide - add payload limitation #8224

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: develop
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
title: AI Endpoints - Features, Capabilities and Limitations
excerpt: Find out about current features, capabilities and limitations of AI Endpoints
updated: 2025-06-13
updated: 2025-08-14
---

> [!primary]
Expand Down Expand Up @@ -58,9 +58,17 @@ If you exceed this limit, a **429 error code** will be returned.

If you require higher usage, please **[get in touch with us](https://help.ovhcloud.com/csm?id=csm_get_help)** to discuss increasing your rate limits.

### Payload size limits

To ensure security and stability, AI Endpoints APIs enforce default request payload size limits:

Most endpoints are limited to **2 MB** per request body. This applies to common input types such as String and Json parameters.

However, some endpoints like those handling audio transcriptions, are specifically configured to accept larger payloads due to their use cases. These endpoints can handle larger audio files, but are limited by audio file size and duration. The specific limits of these endpoints will be indicated in their respective model documentation.

### No usage limit

As of now, the AI Endpoints platform does not impose any usage limits for API requests, apart from the rate limiting.
As of now, the AI Endpoints platform does not impose any usage limits for API requests, apart from the rate and payload size limiting.

However, we are considering introducing a usage limit feature in the future. This feature will allow you to set a limit on the number of tokens, characters, seconds of audio consumed, depending on your usage, providing better control and management over AI Endpoints consumption.

Expand Down