Performance
2x
more relevant results than embeddings and rerankers
the best and fastest
agentic search models
for private data
>1T tokens in production
Traditional search pipelines (“RAG”) drop off rapidly as datasets get bigger or the questions harder. Their only way to improve is adding more steps, paths, and complexity.
Unlike math and coding, search only sees modest gains from increasing model size. Instead, search benefits from looking at more documents. And the cost to see each document increases in lockstep with parameters, limiting the amount of exploration a large model can do.
We start with the atomic unit of search, a small agentic model that reasons and searches in just 300ms and scale it up to dozens of coordinating agents, doing hundreds of searches.
2x
more relevant results than embeddings and rerankers
8x
SID-2
Frontier model
faster than frontier models
20x
cheaper than frontier models
SID-2 is trained to find everything
Scales from super fast single agents to a swarm of 24 for the hardest tasks
agents
Effectively infinite context window with swarms of agents, and 256K tokens for a single agent
One agent 256K
Match reasoning effort & metric to your application
Compatible with your existing search backends and tools. No moving data or reindexing required.
Self-serve on SID API, serverless with ZDR, SOC 2 and HIPAA, or self-hosted in your VPC on any major cloud
89%
quality maintained at 10B items (vs 10k items)
SID is a research center working on new methods for search.