What does your company brain cost?

Cognee runs on local models — on hardware you already own, the whole pipeline is free. Size your documents, code, and database tables below and compare BYOC on local models against the same pipeline on API LLMs.

What goes into the brain

Full pipeline: graph extraction + summarization + embeddings

GB of data

Parsed deterministically (AST) — embeddings only, no LLM calls

repositories

Semi-structured + unstructured mix — one extraction pass + embeddings

GB of data

Every agent run feeds the brain — extraction pass + embeddings

GB of traces

Schema-mapped rows — one small schema LLM pass, then embeddings

k rows
How it runs

Agents and people asking the brain (graph completion, cognee's default)

queries

One cognee Postgres per agent, group of agents, org, or user — hosted on the shared fleet

instances

Workstations or on-prem servers — $0, the whole pipeline is free

Auto-scaled: 1× 48 vCPU / 192 GB node — sized vertically for the data, horizontally for the query volume.

Prices per 1M tokens, as of August 2026

First-year cost · 4,093M tokens ingested once
BYOC · LLM-free CPU runtime — completely free on your own hardware
$245
Same pipeline on GPT-5.5 (API)
$142,543
Pure agentic reasoning, no memory — re-explores the raw data on every query, forever
$252,807

Storage: 255.7 GB total — 243.2 GB of graph/vector/relational data plus 12.5 GB across 25 isolated Postgres instances — included in both tracks at $0.08/GB/mo. Cognee Cloud reference: one-time $4,093 at $1/1M tokens processed.

$0in model + hardware fees on your own machines
$142,298saved in the first year vs GPT-5.5
Alwayscheaper than the API, from the first query
BYOC · LLM-free CPU runtime
Model + embedding fees$0
Initial ingest (~24 h wall-clock on 87 nodes)$0.00
Node fleet / month (1× 48 vCPU / 192 GB node)$0
Storage / month (incl. 25 Postgres instances)$20.45
API · GPT-5.5
Ingest LLM calls (one-time)$141,188
Embeddings (one-time)$636
Query LLM calls / month (2,000 queries)$39.50
Storage / month$20.45
Pure agentic · no memory
Ingest — nothing is remembered$0
Exploration per query (~2,089k tokens read)$10.53
Exploration / month (2,000 queries)$21,067
Every year, again$252,807
Methodology & assumptions
  • 1 GB of documents ≈ 25M tokens (≈10% of document bytes are extractable text — a fixed assumption, measured at 8.65% on a real contract PDF). A GitHub repository ≈ 1M tokens (~100k lines), API data ≈ 25% extractable, agent traces ≈ 50%, and ~40 tokens per database row — all estimates; measure on your data.
  • Each isolated memory instance is its own cognee Postgres hosted on the shared node fleet — per agent, group of agents, org, or user. Modeled at ~0.5 GB base storage and ~0.25 GB RAM per instance (estimates); instance count therefore grows the fleet, not just the disk.
  • The local track runs cognee's LLM-free extraction (GLiNER2-class 205M CPU encoder): measured at ~1.6M pipeline tokens in ~22 minutes on one laptop-class CPU — ~1,200 tokens/sec/node — with zero LLM completions. Nodes auto-scale: vertically so the working set fits RAM, horizontally so ingest lands within 24h and queries stay under 50% utilization. Node rates surveyed August 2026 (Hetzner-class VPS vs AWS r6g on-demand).
  • Query cost models cognee's default graph completion: ~1,550 input / ~400 output tokens per question (top_k=15). Retrieval-only search types cost $0 in model fees on every track; on the local track completions run on a local model.
  • “Pure agentic reasoning” is the no-memory baseline: the agent re-explores the raw data with LLM calls on every query — estimated at ~0.5% of the corpus per question (floor 20k tokens). Past a ~1M-token context budget, every doubling of the corpus adds another ~250k-token exploration round, plus ~3k reasoning tokens out. Nothing is remembered, so the exploration bill repeats every year — and quality degrades as the corpus outgrows what one query can re-read.
  • Documents run the API pipeline at graph extraction (~0.78 output ratio) + summarization (~0.39); code is parsed deterministically (AST, no LLM); database rows take one small schema-mapping pass. Storage uses cognee's embedded defaults (LanceDB, Ladybug, SQLite) at gp3 rates; embeddings are not duplicated onto graph nodes (verified against cognee source). API prices as of August 2026. Cognee Cloud meters $1/1M tokens processed, plus $5/workspace on Standard.
Get started

Cognee is the fastest way to start building reliable Al agent memory.

Cognee Cloud