OVHcloud AI Endpoints
OVHcloud AI Endpoints offers access to a wide range of language models from a European cloud provider, with data sovereignty and GDPR compliance.
Installation
Section titled “Installation”The OpenAI provider is an optional dependency. To install, run:
pip install 'strands-agents[openai]'npm install @strands-agents/sdk openaiGenerate an API key in the OVHcloud Manager under
Public Cloud > AI & Machine Learning > AI Endpoints > API keys,
export it as OVHCLOUD_API_KEY, and point the provider at the AI Endpoints
endpoint:
import os
from strands import Agentfrom strands.models.openai import OpenAIModel
model = OpenAIModel( client_args={ # An empty key selects the rate-limited free tier "api_key": os.environ.get("OVHCLOUD_API_KEY", ""), "base_url": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", }, model_id="Meta-Llama-3_3-70B-Instruct",)
agent = Agent(model=model)response = agent("Explain tool calling in one sentence.")print(response)import { Agent } from '@strands-agents/sdk'import { OpenAIModel } from '@strands-agents/sdk/models/openai'
const model = new OpenAIModel({ api: 'chat', // A non-empty API key is required; the keyless free tier is not supported apiKey: process.env.OVHCLOUD_API_KEY, clientConfig: { baseURL: 'https://oai.endpoints.kepler.ai.cloud.ovh.net/v1', }, modelId: 'Meta-Llama-3_3-70B-Instruct',})
const agent = new Agent({ model })const response = await agent.invoke('Explain tool calling in one sentence.')console.log(response)Configuration
Section titled “Configuration”Two client settings connect the provider to OVHcloud AI Endpoints:
- API key: from the OVHcloud Manager. Without a key, requests use a rate-limited free tier; the Python provider accepts an empty key string, while the TypeScript provider requires a non-empty key.
- Base URL:
https://oai.endpoints.kepler.ai.cloud.ovh.net/v1
Model IDs come from the
AI Endpoints catalog,
for example Meta-Llama-3_3-70B-Instruct. For model parameters and other provider
options, see the
OpenAI provider guide.