Time for a standard

Publishers can call their models whatever sells them. Nobody is arguing with their marketing choices; one line alongside the name is all it takes to say what the name does not:

Names and their model URIs
The nameAlways the current onePinned to this release
GPT-6.2 Astramodel:openai/text/ultramodel:openai/text/ultra:6.2
Gemini 4 Hydrogenmodel:google/text/coremodel:google/text/core:4
Claude Haiku 5.5model:anthropic/text/lightmodel:anthropic/text/light:5.5

ultra is the flagship, core the everyday default, light the fast, cheap rung. Leave the version out and the line follows the next launch on its own. Pin it only where a result must be reproduced.

Switch provider by changing one word:

model:openai/text/core
model:google/text/core
model:anthropic/text/core

Each line is that publisher's everyday default. Same role, not the same results.

A few things a product name cannot express:

What one line can say
model:anthropic/text/core@bedrockThe same model served by someone else, under the same name.
model:anthropic/text/ultra-restrictedA model restricted to selected operators, flagged directly in the identifier.
model:alibaba/text/core-open/35b-a3b/mxfp4@localThe newest open Qwen at the size and precision your GPU fits.

The moratorium

Nobody has to give up a brand. The moratorium asks for four small, verifiable commitments from publishers and tooling rather than from application developers:

  1. Publishers: publish a model URI next to the native name in model cards and in the model-listing API response (one extra field).
  2. Publishers: place every model on the shared six-rung scale at release, with at most one model per slot (rung, scope, suffixes and size). A new model in an occupied slot replaces the old one.
  3. Publishers: never change the model behind a pinned version. An update gets a new version.
  4. Routers, gateways and local inference engines: accept a model URI as an alias of the native name.

This is an appeal. By signing, developers ask publishers and tooling to take on these commitments, and adopt model URIs in their own configuration files and documentation, with the native name as a fallback until both sides support them.

The working draft

A model URI says what role a model plays in its publisher's lineup, who may use it, how it is licensed and where it runs. It carries verifiable facts only, with no quality scores or opinions.

model:publisher/scope/tier
      [-special][-access][-weights]
      [/size][/quant][:version][~derivation][@host]

Written on one line, without spaces. Only the first three parts are required.

Parts of a model URI
PartQuestion it answersValues
publisherWho made the model?A registered organisation name: anthropic, google, alibaba
scopeWhat does it produce?text omni image video audio tts transcribe embed rerank decision
tierWhich role in the lineup?nano light core high max ultra
specialWhat is it published for?A registered specialisation: code, rt, base, guard, ocr, research, gui, medical, voiceclone, …
accessWho may use it?restricted gov internal
weightsCan the weights be downloaded?open unmodified OSI-approved licence, weights any other downloadable licence
sizeHow big is it?Total parameters (m, b, t), plus active ones for MoE: 35b-a3b, 2.4t-a95b
quantAt what precision does it run?q4 fp8 mxfp4
versionWhich release?Leave it out for the current model, or pin the publisher's number
derivationDid a third party modify it, and how?Author and kind: huihui-abliterated
hostWhere does it run?local, edge, bedrock, vertex; absent means the publisher's API

The tier is a role, not a score

Tiers and their roles
TierRole
nanoThe smallest and cheapest, for simple high-volume tasks
lightFast and inexpensive
coreThe publisher's everyday default
highA step above the default, for harder work
maxJust below the flagship
ultraThe publisher's flagship

The scale is the same for every publisher. A publisher that adopts the standard declares the tier at release and fits its lineup to the scale rather than stretching the scale to fit. Until it does, the registry assigns the tier: core is the model the publisher presents as its everyday default, ultra its flagship, and the others are placed by list price.

Four rules that keep it stable

Examples

Example model URIs
ModelModel URI
GPT-6.2 Astramodel:openai/text/ultrapinned: model:openai/text/ultra:6.2
GPT-6 Lunamodel:openai/text/nanopinned: model:openai/text/nano:6
Gemini 4 Carbonmodel:google/text/ultrapinned: model:google/text/ultra:4
Claude Sonnet 5.5 on Bedrockmodel:anthropic/text/core@bedrockpinned: model:anthropic/text/core:5.5@bedrock
Claude Mythos 5.2, selected operators onlymodel:anthropic/text/ultra-restricted:5.2
A government-only editionmodel:example/text/core-gov:2.0
Mistral Codestralmodel:mistral/text/core-codepinned: model:mistral/text/core-code:25.08
Gemini 2.5 Computer Use (GUI & browser control)model:google/text/core-guipinned: model:google/text/core-gui:2.5
Gemini Deep Research Previewmodel:google/text/core-researchpinned: model:google/text/core-research:2026.04
Baichuan M2, medical, 32Bmodel:baichuan/text/core-medical-open/32b@localpinned: model:baichuan/text/core-medical-open/32b:2@local
Qwen 3.6 MoE, 35B total, 3B active, MXFP4model:alibaba/text/core-open/35b-a3b/mxfp4@localpinned: model:alibaba/text/core-open/35b-a3b/mxfp4:3.6@local
The same model, abliterated by a third partymodel:alibaba/text/core-open/35b-a3b/q4:3.6~huihui-abliterated@local
Gemma 4, 26B total, 4B active, Q4 (Apache-2.0)model:google/text/core-open/26b-a4b/q4@localpinned: model:google/text/core-open/26b-a4b/q4:4@local
Meta Llama 4 Maverick (community licence; one size on this rung)model:meta/text/core-weights@localpinned: model:meta/text/core-weights:4@local
GPT Realtime 2.1 (real-time duplex voice)model:openai/omni/core-rtpinned: model:openai/omni/core-rt:2.1
MiMo-V2.5-TTS VoiceClonemodel:xiaomi/tts/core-voiceclonepinned: model:xiaomi/tts/core-voiceclone:2.5
Lyria 3 Pro Preview (music & non-speech audio)model:google/audio/corepinned: model:google/audio/core:3
Liquid d1 (typed probabilistic decision)model:liquid/decision/corepinned: model:liquid/decision/core:1

Tiers are assigned with the registry rule from the publishers' own descriptions and price lists, as of 21 November 2026. No publisher has declared them yet. More examples are in SPEC.md.

What it is not

The full draft has the grammar, a reference regex, the registry format, security considerations and the open questions: read the specification.

The repository already includes a seed registry built from models.dev (over 400 models from more than 60 publishers), a list of incompatible catalogue entries (missing evidence, rolling aliases, slot collisions, parameter splits and opaque sizes), a small Node CLI resolver and generated LiteLLM aliases.

Sign, or break it

This is a working draft, not a finished standard. It gets better when people attack it.

Sign via pull request Open an issue on the draft

To sign, add one line with your name, role and an optional link to SIGNATORIES.md. To object, open an issue. An edge case the grammar cannot express is the most useful report you can send.