New Model - Llama-4-Scout-17B-16E

[mhrng]

User story

As a software developer/web developer/AI engineer,
I would like to be able to use the Llama-4-Scout-17B-16E model through AI Endpoints

so that I can leverage its advanced capabilities in natural language generation, visual reasoning, and multilingual support to build applications that can process and understand text and images, generate synthetic data, etc.

ETA

June 2025 (TBC)

Acceptance criteria

• Llama-4-Scout-17B-16E model is deployed on a secure and scalable infrastructure
• I can test the model on AI Endpoints dedicated website: https://endpoints.ai.cloud.ovh.net/
• I can access the model via an API endpoint for a seamless and serverless integration with applications and tools, supporting multiple languages
• I can use API key authentication to access my API in a secured way, with the ability to config API key duration and eventually revoke access
• I can observe and monitor my usage of the model through the OVHcloud Control Panel WW (but US) with access to metrics
• I have access to a detailed documentation and code examples in order to get started with the model

Follow, vote and give your feedback

You can follow this task with the notification on the right tab.
Ask us anything here in the comments below, and vote with emojis for most requested items!
👍 to vote for this issue

Discuss on Discord

Feel free to discuss with us on https://discord.gg/ovhcloud