LLM-native web search, delivering industry-leading real-time intelligence with the lowest latency and enterprise-grade reliability.


Search the live web for images from a text query, or start from a reference image to find visually similar results.
Search the live web for videos from a text query, returned with rich metadata and ready to preview, embed, or pass to a model.

Beyond search
Pull clean content from any URL, and embed meaning with the #1 retrieval model for text and vision.
The #1 text embedding model for retrieval. Built specifically to find what your agents need.SOTA on RTEB
The #1 multimodal embedding model for retrieval. One embedding space across text, images, videos, and visual documents.SOTA on MMEB-v2
Turn any URL into clean markdown, with intent-focused highlights and page classification.
## iPhone Meet the latest iPhone lineup. ![iPhone 17 Pro, back exterior, deep blue color, Pro Fusion camera system in top left corner, Apple logo in center, iPhone 17, back exterior, white color, Dual Fusion camera system in top left corner, Apple logo in center, iPhone 17e, back exterior, soft pink color, Fusion camera system in top left corner, Apple logo in center,iPhone Air, sid…
Top 3 on speed, cost and quality
#1 for speed, #2 for cost and top 3 for quality in the Artificial Analysis Search API Benchmark. One product, in its default configuration. Read the blog →
| Provider | Search Index | Cost per task | Time per task | Time per query |
|---|---|---|---|---|
| 77 | $0.024 | 13.6s | 0.21s | |
| 80 | $0.064 | 34.7s | 3.27s | |
| 80 | $0.070 | 28.5s | 1.07s | |
| 75 | $0.059 | 37.7s | 2.66s | |
| 75 | $0.079 | 20.0s | 0.44s | |
| 74 | $0.067 | 19.1s | 0.72s |
Search infrastructure for agents. Ready in 3 steps.