Distributions

A distribution is a deployable artifact or execution variant: for example, a quantization, local package or cloud route. It can link to a concrete canonical model or a model family without collapsing checkpoint identities.

Summary reads omit large registry configuration and manifest fields. include_details=true requests the full source artifact and lowers the maximum page size to 100. Inactive artifacts are excluded by default. Historical changes are scoped by both source and source_model_id.

On a model-scoped request the canonical model or family in the path determines that scope. The worker records observations; GET requests do not pull or download model weights.

On this page

Search deployment and quantization variants

GET /api/v1/distributions

Access: public read; no TensorTrace API key.

Parameters

NameLocationRequiredType / limitsMeaning
sourcequeryNostringRegistered data-source ID, such as openRouter. This identifies the collecting source, not necessarily the model developer.
familyqueryNostringExact canonical model-family ID; it groups related deployment artifacts without merging checkpoint identities.
modelqueryNostringExact canonical_model_id to which the artifact is linked.
source_model_idqueryNostringExact model or artifact identifier used by the collecting source.
qqueryNostringCase-insensitive substring of the source artifact identifier.
execution_modequeryNostring Values: local, cloudRestrict artifacts to local or cloud execution.
include_detailsqueryNobooleanInclude full source artifact metadata. Default false; true lowers the maximum limit to 100.
include_inactivequeryNobooleanInclude previously observed artifacts that are no longer active. Default false.
limitqueryNointeger Default: 100; Minimum: 1; Maximum: 1000Maximum number of returned rows. The documented default and range apply; numeric pagination limits are clamped unless stated otherwise.
offsetqueryNointeger Default: 0; Minimum: 0Zero-based number of matching rows to skip. Default 0; negative values are clamped to 0.

Request example

curl 'https://tensortrace.net/api/v1/distributions?limit=1'

Responses

StatusMeaningBody type
200Source-linked artifacts; large original metadata is optional.DistributionResponse
400Invalid queryNo declared JSON body
404Unknown modelNo declared JSON body

Response example · 200

Illustrative values; schema-valid and not a live catalog measurement.

{
    "data": [
        {
            "source_id": "openRouter",
            "source_model_id": "google/gemini-2.5-flash",
            "family_model_id": "example",
            "canonical_model_id": "google/gemini-2.5-flash",
            "execution_mode": "local",
            "receipt_id": "00000000-0000-4000-8000-000000000001",
            "discovery_receipt_id": "00000000-0000-4000-8000-000000000001",
            "identity_relation": "deployment_of"
        }
    ],
    "total_count": 1
}
FieldTypeRequiredMeaning / constraints
dataarray of DistributionYes
total_countintegerYesMinimum: 0

List variants for a canonical model or family

GET /api/v1/models/{provider}/{model}/distributions

Access: public read; no TensorTrace API key.

Parameters

NameLocationRequiredType / limitsMeaning
providerpathYesstringCanonical model publisher namespace; URL-encode this path segment.
modelpathYesstringCanonical model name within the publisher namespace. URL-encode nested slashes in this single segment.
sourcequeryNostringRegistered data-source ID, such as openRouter. This identifies the collecting source, not necessarily the model developer.
familyqueryNostringExact canonical model-family ID; it groups related deployment artifacts without merging checkpoint identities.
modelqueryNostringExact canonical_model_id to which the artifact is linked.
source_model_idqueryNostringExact model or artifact identifier used by the collecting source.
qqueryNostringCase-insensitive substring of the source artifact identifier.
execution_modequeryNostring Values: local, cloudRestrict artifacts to local or cloud execution.
include_detailsqueryNobooleanInclude full source artifact metadata. Default false; true lowers the maximum limit to 100.
include_inactivequeryNobooleanInclude previously observed artifacts that are no longer active. Default false.
limitqueryNointeger Default: 100; Minimum: 1; Maximum: 1000Maximum number of returned rows. The documented default and range apply; numeric pagination limits are clamped unless stated otherwise.
offsetqueryNointeger Default: 0; Minimum: 0Zero-based number of matching rows to skip. Default 0; negative values are clamped to 0.

Request example

curl 'https://tensortrace.net/api/v1/models/google/gemini-2.5-flash/distributions?limit=1'

Responses

StatusMeaningBody type
200Source-linked artifacts; large original metadata is optional.DistributionResponse
400Invalid queryNo declared JSON body
404Unknown modelNo declared JSON body

Response example · 200

Illustrative values; schema-valid and not a live catalog measurement.

{
    "data": [
        {
            "source_id": "openRouter",
            "source_model_id": "google/gemini-2.5-flash",
            "family_model_id": "example",
            "canonical_model_id": "google/gemini-2.5-flash",
            "execution_mode": "local",
            "receipt_id": "00000000-0000-4000-8000-000000000001",
            "discovery_receipt_id": "00000000-0000-4000-8000-000000000001",
            "identity_relation": "deployment_of"
        }
    ],
    "total_count": 1
}
FieldTypeRequiredMeaning / constraints
dataarray of DistributionYes
total_countintegerYesMinimum: 0

GET /api/v1/distributions/history

Access: public read; no TensorTrace API key.

Parameters

NameLocationRequiredType / limitsMeaning
sourcequeryYesstringRegistered data-source ID, such as openRouter. This identifies the collecting source, not necessarily the model developer.
source_model_idqueryYesstringExact model or artifact identifier used by the collecting source.
limitqueryNointeger Default: 20; Minimum: 1; Maximum: 100Maximum number of returned rows. The documented default and range apply; numeric pagination limits are clamped unless stated otherwise.
offsetqueryNointeger Default: 0; Minimum: 0Zero-based number of matching rows to skip. Default 0; negative values are clamped to 0.

Request example

curl 'https://tensortrace.net/api/v1/distributions/history?source=example&source_model_id=google%2Fgemini-2.5-flash&limit=1'

Responses

StatusMeaningBody type
200Source-linked artifacts; large original metadata is optional.object
400Invalid queryNo declared JSON body
404Unknown modelNo declared JSON body

Response example · 200

Illustrative values; schema-valid and not a live catalog measurement.

{
    "data": [
        {}
    ],
    "total_count": 1,
    "limit": 1,
    "offset": 0
}
FieldTypeRequiredMeaning / constraints
dataarray of objectYes
total_countintegerYes
limitintegerYes
offsetintegerYes

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace