WebSearch
WebSearch allows your Clovis models to access the Web in real time, enriching their responses with up-to-date information.
Concretely, your model can:
- launch web searches,
- analyze and synthesize recent content,
- provide reliable and contextualized answers.
WebSearch is exposed as an MCP server that your application, agent, or orchestrator can call directly.
Some models natively integrate WebSearch without MCP declaration. See the Native WebSearch — GPT-OSS page to learn more.
Prerequisites
A valid Clovis API key (Bearer token)
The API key must have access to WebSearch
The models used must be authorized for this key
Network access to the Clovis gateway: https://llm-gateway.clovis-ai.fr
If you don't have an API key yet, contact your Claranet account manager.
Configuration
Connecting to WebSearch only requires two elements:
# Clovis gateway URL
CLOVIS_BASE_URL=https://llm-gateway.clovis-ai.fr/v1
# Your API key
CLOVIS_API_KEY=sk-xxxx
The platform handles all backend complexity (routing, orchestration, search execution).
Endpoint
/v1/responsesPOST https://llm-gateway.clovis-ai.fr/v1/responses
Authorization: Bearer <CLOVIS_API_KEY>
Content-Type: application/json