A hand-curated, source-backed catalogue of AI models.
Each entry records what a model is, what it can do, where it can be called, and what it costs. Every fact has a source. The catalogue is maintained by hand and reviewed like code, so one place answers "which models exist and what are they" for every Grida product.
Optional illustrative costs explain a specific scenario separately from published rates. They carry explicit manual provenance and may omit source links when no durable reference exists.
Status: early. The catalogue is at schema version 2. Snapshots are published as GitHub Releases; see Get the catalogue.
Every change to the catalogue on main is published as a
release and as the npm package
@grida/ai-models, which holds the same
files and no code.
npm install @grida/ai-modelsimport models from "@grida/ai-models/models.json" with { type: "json" };For fetching at runtime, use the package through jsDelivr's CDN: compressed, cached at the
edge, and with no redirects. @2 follows the newest snapshot of schema version 2; a full
version pins one snapshot.
https://cdn.jsdelivr.net/npm/@grida/ai-models@2/models.json
The GitHub Release assets suit scripts and archiving. The newest snapshot is always at:
curl -LO https://github.com/gridaco/models/releases/latest/download/models.v2.json
curl -LO https://github.com/gridaco/models/releases/latest/download/labs.v2.jsonThe v2 in the file name is the schema version. GitHub latest follows the newest
release across schema majors. Assets keep versioned names, so an old asset name
stops resolving after a major change instead of serving a different shape. To pin
a snapshot, use its version instead of latest:
https://github.com/gridaco/models/releases/download/<version>/models.v2.json.
Each release holds:
| asset | contents |
|---|---|
models.v2.json, labs.v2.json |
Model cards and labs (catalogue/models.json, catalogue/labs.json) |
models.v2.schema.json, labs.v2.schema.json |
Their JSON Schemas |
grida-models-<version>.tar.gz, .zip |
The whole catalogue, logos included, with LICENSE and manifest.json |
manifest.json |
Version, schema version, source commit, content digest, counts, and the SHA-256 of every file |
SHA256SUMS |
Checksums of the other assets: sha256sum -c SHA256SUMS --ignore-missing |
Versions read v<schema>.<YYYYMMDD>.<n>: the schema version,
the UTC date of the source commit, and a counter for snapshots on the same day. They are valid
semver, so a range such as ^2 follows every snapshot without crossing a breaking schema
change. A release is published only when the catalogue's content changes, and the archives
are reproducible from the same commit. Release notes list the models, labs, schemas, and
other files that changed since the previous release.
The authored schema changelog explains contract changes, compatibility and consumer migration. It is included in snapshot archives and the npm package, and linked from generated release notes. Ordinary model and price updates remain in those release notes rather than growing the schema log.
Version 2 lets a decision offering omit underlying_model when no relationship is
documented. Its existing meaning and all other record fields are retained. A new
record without that field fails the version 1 schema, so update the validator and
handle an absent relationship before selecting a version 2 snapshot. The Models
$schema value and both published schema $ids now end in v2.
Existing npm ^1 ranges and CDN @1 URLs stay on version 1. Immutable version 1
release URLs remain available, for example:
https://github.com/gridaco/models/releases/download/v1.20261113.1/models.v1.json
https://cdn.jsdelivr.net/npm/@grida/[email protected]/models.json
Publishing the first version 2 release moves GitHub latest. Moving URLs such as
releases/latest/download/models.v1.json and the matching labs/schema assets then
stop resolving. Choose an explicit old tag to remain on version 1, or update both
the asset names and reader to version 2. Labs retain their record shape; both
schemas and asset names follow the catalogue's single release major.
The catalogue data is MIT licensed. Lab logos are trademarks of their owners and are not covered by that license.
Snapshots describe public model facts, not a consuming application's live offering. For models currently served by Grida, see the model directory or Gateway discovery.
When updating a consumer, handle unfamiliar optional display metadata gracefully rather than reject the whole catalogue. Execution and pricing fields still need explicit support. Coordinate breaking contract changes with consumer updates.
Model metadata fragments quickly. The same model ID, context window, price, or release date ends up in an application package, a gateway's route table, a pricing page, a marketing section, and a CLI, and each copy drifts on its own schedule. A stale entry is not a conservative answer; it is a wrong one.
This repository is meant to be the single place those facts are authored. Everything else consumes a projection of it.
| Kind | Examples |
|---|---|
| Identity | Canonical ID (vendor/model), label, vendor, family (text, image, video, audio, 3D, …) |
| Release provenance | First broad public release date, its basis, and the first-party source URL |
| Capabilities | Modalities, accepted image formats, tool calling, audio, transparent background |
| Limits | Context window, output limit, sizes, aspect ratios, durations, size constraints |
| Provider bindings | Exact provider IDs, a native API reference, and sourced coverage/exclusion reasons |
| Model distribution | Official code and weight links, exact variants, access conditions and separate licenses |
| Published prices | Public list prices per provider, in the provider's own billing unit |
| Published calculators | Sourced output-token formulae, examples, and image-input tokenization rules |
- Not a router or SDK. A provider binding records that an endpoint exists and what it costs. It does not implement a client or grant permission to call it.
- Not billing execution. The catalogue holds publicly advertised regular prices, including Grida's public service price. Funding fees, credit conversion, margins, supplier selection and negotiated/account-specific rates stay with their owners.
- Not a live mirror. Nothing is scraped into this repository automatically. Discovery tools such as models.dev give leads; a person verifies each fact against a first-party source.
- Not an endorsement. Being catalogued does not mean any Grida product offers the model. Which models a product lists, and in what order, is that product's decision.
Each model is authored as one TOML card in models/, grouped by lab
(models/openai/gpt-5.5/card.toml). The contract consumers read,
catalogue/models.json, is generated from those cards: plain JSON
with a JSON Schema, readable from any language. Its shape and rules are documented in
catalogue/README.md.
- Every fact has a source. Prices, limits, and release dates cite a first-party page.
- Regular prices, without promotion tracking. Record sourced, non-promotional provider rates even during an active discount. Do not maintain discounted prices or promotion expiry dates. Existing models remain available for consumer review; provider coverage changes do not silently remove them.
- An ID is never portable. The same model has different IDs, availability, parameters
and prices on different providers. Bindings retain those differences. A sourced native
reference_provideris presented first; it does not choose a consumer's route. - Additive by default. Consumers depend on the shape. Fields are added; breaking changes get a new schema version.
- The contract is language-agnostic. Consumers read JSON, JSON Schema, and provenance notes. Tooling and tests use whichever language fits (currently Python). Typed bindings and code generation live in each consumer.
- One card per model. Facts are authored as TOML cards in
models/<lab>/<model>/, andcatalogue/models.jsonis generated from them. A card's directory leaves room for per-model material such as example assets. - Labs are registered. Each lab directory holds a
lab.tomlwith the lab's display name, first-party homepage, and official logo, published ascatalogue/labs.jsonandcatalogue/logos/. A card'svendoris a lab ID. - Snapshots are GitHub Releases and an npm package. Each content change to
catalogue/onmainis published as a versioned, checksummed release and as@grida/ai-modelson npm, through trusted publishing (scripts/release.py,.github/workflows/release.yml). - Facts only. Product policy (which models a product lists, its tiers and defaults) stays with each product.
These are deliberately undecided, and are tracked here so nobody mistakes them for settled.
- Hosted endpoint. Whether to serve the catalogue from a domain of its own, beyond GitHub Releases, npm, and the CDNs that mirror npm.
- Provider registry. Whether this repository also owns display labels, logos, and ID-prefix rules for providers.
Add or correct a model by opening a pull request that changes its card in
models/, regenerates catalogue/models.json, and cites a first-party source
for every new fact. Contributor and agent conventions live in
AGENTS.md and .agents/skills/.
A public contract change also updates the schema changelog in the same PR, including compatible extensions and changes to consumer-visible validation or generation semantics. Explain the before/after behavior, compatibility and migration. The PR schema-content check catches a missing log update for changed JSON Schemas; reviewers must also check semantic changes implemented elsewhere. Catalogue-only model, provider and price changes need no schema entry.
MIT. The lab logos in models/ and catalogue/logos/ are trademarks of their
owners and are not covered by this license; each lab's entry links its source and, where
published, its brand guidelines.