Cloudflare Introduces Web Search API Integration via AI Gateway
Cloudflare has launched native Web Search API integration within AI Gateway in partnership with Ceramic.ai, Exa, and Linkup, allowing developers to easily inject real-time web context into model inference calls.
Cloudflare has announced the integration of native web search capabilities into its AI Gateway, partnering with search providers Ceramic.ai, Exa, and Linkup. This update allows developers to enrich their large language model prompts with real-time web data directly during the inference phase, improving the accuracy and relevance of AI responses without needing separate retrieval setups.
Primary source
Open Cloudflare Blog ↗This article summarizes the source. Check the original for full details and conditions.
Comparison
| Aspect | Before / Alternative | After / This |
|---|---|---|
| Integration approach | Writing custom scraping and search integration code manually before sending data to LLMs | Enabling native Web Search API directly within the AI Gateway pipeline |
| Provider management | Managing separate SDKs, keys, and endpoints for individual search providers | Using a unified interface with support for Ceramic.ai, Exa, and Linkup |
| Observability and caching | Building custom caching and logging layers for web search queries | Leveraging built-in AI Gateway analytics, caching, and rate limiting |
Action Checklist
- Select a partner search provider from the supported list Supported partners currently include Ceramic.ai, Exa, and Linkup
- Configure the Web Search API credentials in the Cloudflare Dashboard Ensure your provider API keys are correctly mapped in your AI Gateway settings
- Update inference calls to use AI Gateway REST APIs or Workers bindings Modify your model calls to include the new search parameter parameters
- Monitor search latency and query caching in the AI Gateway analytics tab Check the dashboard to verify search responses are cached correctly to save costs
