Search—API—Platform

Deterministic search API
without the inference cost

Search 48.4M knowledge entries or bring your own data. Tokenized with 2.8M whole words. No LLM embeddings. No inference costs.

2.8M
Whole-Word Vocabulary
35
Knowledge Domains
0
LLM Inference Calls
100%
Deterministic
Quick Start

Deterministic search in two API calls

quickstart.js
// 1. Create an index — no embedding pipeline
await fetch("https://cold-api.coldstate.ai/v1/indexes", {
  method: "POST",
  headers: {
    "Authorization": "Bearer cs_live_...",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    name: "acme-docs",
    domain_preset: "general",
    documents: [
      { id: "doc_001", content: "Parental leave policy..." },
      { id: "doc_002", content: "Remote work guidelines..." }
    ]
  })
});

// 2. Search — deterministic, Ψ-scored
const res = await fetch(
  "https://cold-api.coldstate.ai/v1/indexes/idx_.../search",
  {
    method: "POST",
    headers: { "Authorization": "Bearer cs_live_..." },
    body: JSON.stringify({
      query: "parental leave policy for remote employees",
      limit: 5
    })
  }
).then(r => r.json());

// res.results[0].state: "CRYSTALLINE"
// res.results[0].score["Ψ"]: 0.94
// res.diagnostics.execution_time_ms: 847
Comparison

A deterministic search API vs. the RAG stack

Embedding pipeline
Traditional: Required at index + query
ColdState: None — zero LLM cost
Per-query cost
Traditional: Embed + vector + rerank
ColdState: Single QST navigation
Result consistency
Traditional: Probabilistic (varies)
ColdState: Deterministic (identical)
Infrastructure
Traditional: Multi-node clusters
ColdState: Single Cold-State engine
Topology signal
Traditional: Not available
ColdState: CRYSTALLINE · FLUID · REACTIVE

This is what we call Deterministic Knowledge Infrastructure. See why deterministic retrieval matters, how it stacks up in RAG alternatives, explained, or go straight to the API reference and pricing.

Try it live

Search it. Then prove it's deterministic.

A real, read-only index running on the live API. Run a query, expand any result to see the per-term scoring, then verify the same query returns a byte-identical ranking every time.

Pick a query above, or type your own.
FAQ

Deterministic search, explained

What is a deterministic search API?

A deterministic search API returns the same ranked results for the same query, every time. ColdState computes relevance from whole-word tokenization (a 2.8M-word vocabulary) and transparent scoring instead of LLM embeddings — so rankings are reproducible, explainable, and cacheable. There is no model inference, no temperature, and no drift between runs.

How is ColdState different from vector databases and embedding search?

Vector search embeds your query with a neural model and finds approximate nearest neighbors — results can shift between model versions, and every query pays an inference cost. ColdState indexes documents once and scores them deterministically at query time: no embedding step, no approximate search, no GPU. The explain endpoint shows exactly why a document ranked where it did, token by token.

Does ColdState have an MCP server?

Yes. ColdState hosts a Model Context Protocol (MCP) server with 16 read-only tools — search the global knowledge base, fetch an entry verbatim, cite it, verify it later, find related entries, and search, browse, and explain your own indexes — so Claude and other MCP-compatible AI assistants can use ColdState directly. It runs over HTTP with the same API key, so there is nothing to install.

Why does deterministic retrieval matter for AI agents?

Agents built on stochastic retrieval are hard to debug: the same prompt can fetch different context on every run. Deterministic retrieval makes agent behavior reproducible — evals are stable, failures replay exactly, and every ranking decision can be audited after the fact.

What is the global knowledge base?

Alongside your own indexes, ColdState exposes a curated knowledge base of 48.4 million entries across 35 domains — science, medicine, technology, law, history, and more — searchable through the same deterministic API and MCP tools.

Can I download my index instead of hosting it?

Yes. IaaS (Indexing as a Service) mode builds your index server-side and delivers it as a portable SQLite file you can query offline — no ongoing hosting relationship. Hosted mode keeps the index on ColdState with encrypted-at-rest storage.

Ready to go cold?

Search our knowledge base or bring your own data. Get your API key and start in under a minute.

Get API Key