GeoBit Large Spatial Model

Add your data, press Start, get a project full of maps and a cited report.

Upload everything you have into a project: files in any format, databases, services, documents and PDFs. Press Start, and out comes a project full of maps, charts and images, and a report that cites every claim.

One model behind one API, with MCP and an optional UI. Blank by default: it ships no customer data and runs on your data alone. Bring your own provider keys. Any basemap. Every major format in and out.

Replaces ArcGIS GeoAI, and the parts of Spatial Analyst, Spatial Statistics and ModelBuilder the Start loop covers.

Sample projects

26 industries, each at a real place

One sample project per industry, at a real place with synthetic data: ten or more datasets each, the mix a customer in that industry would upload. Start was pressed on every one in describe mode with the local model. Each dot opens that sample's maps, charts and cited report.

Maps, charts and report exported (3)Report and charts exported (23)
26sample projects
587output layers
581maps made
741charts made
1,372findings, none uncited

Start with the fully exported samples

These three runs were exported with every map and chart image. The other 23 carry their cited report and chart specs.

All 26 sample projects

How it works

From uploads to a cited report in one press

Upload everything you have into a project, press Start, and out comes a project full of maps, charts and images and a cited report.

  1. 1

    Add everything

    Files in any format, a database URL, a service URL (WMS, WMTS, WFS, OGC API, ArcGIS, XYZ, STAC), a bucket, a sheet, documents and PDFs. All into one project.

  2. 2

    It reads and understands it

    Every dataset is profiled (fields and their meaning, extent, time span), documents are read and their places extracted, relationships between datasets are found. No model call is needed for this.

  3. 3

    Press Start

    With or without a goal. A deterministic recommender proposes analyses from the data shapes, a council of models sizes the run, and as many analyst agents as the job needs run them in parallel, each with checks.

  4. 4

    A project full of maps, and the report

    Every analysis becomes a saved map with a styled layer, an image with legend, north arrow and scale bar, a chart where one fits, and a vision read. The report cites every claim.

  5. 5

    Export, then ask

    Any format, any map client, a run bundle with a manifest. Chat is a separate capability for questions about the data and the results.

What comes out

Maps, charts and a report you can check

Every image below comes from a sample run's export; each sample's page links the original files.

Terrain: elevation with hillshade

A map image for every analysis

With legend, north arrow and scale bar, saved with a styled layer. Shown: terrain: elevation with hillshade, from the telecom sample in Medellin.

Timeline: events per month by dataset

A chart where one fits

A time series when the data has time. Shown: timeline: events per month by dataset, from the public safety sample in Chicago.

  • EvidencedThe timeline counts 2,484 dated events in Incidents, Street light outages, Calls for service by beat and month per month, from October 2024 to September 2026 1234.
  • EvidencedBy dataset: Incidents 1,680; Street light outages 420; Calls for service by beat and month 384 15.
  • EvidencedThe trend is +11.8 events per month; the second half of the months has 2,292 against 192 in the first (+1093.8%) 1.

A report that cites every claim

To a tool result, a layer, a document page or an image; as JSON, Markdown, Word and PDF. Shown: the first findings of the public safety report.

Inside

The GIS toolbox, run by agents

Built on the shared GeoBit kit, so it looks, behaves, syncs and bills like every other GeoBit product.

207 GIS operations as tools

The GIS analysis engine as tools, with its outputs saved as layers, one style source, pipelines and a per-operation OpenAPI.

Terrain

Slope, aspect, hillshade, viewshed, line of sight, least-cost path, hydrology, mobility, terrain forms, solar, stability, volume, suitability and comms coverage. Elevation comes from the project or Copernicus GLO-30, never from a basemap vendor.

Raster, imagery, geostatistics, elevation

The sibling engines linked read-only as tools: raster, geostatistics, elevation and imagery.

Agents with checks

A planning council, a routing ladder with budgets and an analyst swarm, plus chat-over-data tools (filters, read-only SQL over PostGIS) and a watcher.

Outputs you can export

A render worker that draws the same page as the UI, charts, vision reads, the report builder and exports in every major format.

One API, MCP and an optional UI

Projects, datasets, Start and runs, analysis and pipelines, render, charts, report, exports, chat, agents, automations, insights, memory, OGC and tiles.

How it behaves

Your data, your keys

  • Blank by default. It ships no customer data and runs on your data alone, with an opt-in Enrich step for GeoBit layers and clean-license administrative boundaries.
  • Bring your own provider keys. Calls made with your own keys are billed by that provider.
  • Any basemap, every major format. Any map client, every major format in and out.
  • Reading your data needs no model call. Profiles, places and relationships come from the data itself.
  • No paid model call runs on a schedule. Watch mode uses deterministic detectors only.
  • No Esri or QGIS software. Their file formats are read as data.
One API

Every capability behind one API

With MCP for AI assistants and an optional UI. An API reference, an OpenAPI schema and a developer portal come with it.

projectsdatasetsstartrunsanalysispipelinestoolsrenderchartsreportexportschatagentsautomationsinsightsmemoryogctilesmcp
Pricing

Plans in tokens

1,000 tokens are USD 1. A plan includes tokens every month, for less than the same tokens in packs. Plan tokens are spent first; tokens you buy on top never expire.

Starter

+20% tokens
$25/ month
30,000 tokens each month

Worth USD 30 at the token price; plan tokens expire at the end of each period.

Choose Starter

Team

+40% tokens
$200/ month
280,000 tokens each month

Worth USD 280 at the token price; plan tokens expire at the end of each period.

Choose Team

Enterprise

By invoice

Tokens, terms and support agreed with you, billed monthly by invoice.

Get in touch

Pay as you go instead: token packs from 10,000 tokens (USD 10); packs of 50,000 tokens and more carry a bonus of 5% or more. Purchased tokens never expire.

Sign up
  • Plan tokens are granted at the start of each monthly period and expire at its end.
  • Purchased tokens (packs and top-ups) never expire.
  • Plan tokens are spent first; purchased tokens only after the period's plan tokens are used up.
  • Auto top-up is optional: when your balance falls under your threshold it buys the pack you chose, never more than your monthly cap.
  • Switching plans is prorated through Stripe: you pay the difference for the rest of the period and the period's included tokens change by the same share.
  • Canceling keeps your purchased tokens; the plan's tokens last until the end of the period you paid for.
  • Your balance never goes negative; a call your balance cannot pay is refused before it runs.

Bring your own data and press Start.

Sign up at lsm.geobit.ai, add your files, services and documents to a project, and get your own maps, charts and cited report.