Facets

Facets provide valid discovery controls and counts from prepared local data. Use the model-specific and leaderboard-specific endpoints when building those views; the combined endpoint also includes price and source facets.

models.model_types counts published models matching each primary or secondary classification. Use its value with model_type; counts match that filter before pagination. Types and capabilities have separate memberships and counts, so MLLM classification does not share the generic Multimodal capability count. The serial preparation pipeline publishes these counts in descending order. Older prepared responses can omit model_types. The Web groups types before capabilities, orders each group by count then label, and omits Type not reported from the selection menu. The API retains unknown for explicit queries.

Values are identifiers, not presentation labels. Keep the ID when sending a filter and use the supplied label/logo for display. A facet count describes its own published scope; it should not be treated as an intersection count for every active filter.

models.developers contains canonical author organizations, including their publisher aliases. Its order follows each developer's strongest model: Intelligence Index first, capability score next, then Arena rating and name. Send its value as developer. models.providers remains the raw publisher namespace list for the provider parameter.

models.inference_providers contains serving sources with indexed models, ordered by model count and name. Send its value as inference_provider. Editor availability such as GitHub Copilot and Cursor belongs here when models can be linked; it does not establish a standalone API or token price. Both organization lists are rebuilt by the serial preparation pipeline and served with the model facets, without a request-time ranking join.

On this page

Read combined discovery filters

GET /api/v1/facets

Access: public read; no TensorTrace API key.

Parameters

This operation has no path or query parameters.

Request example

curl 'https://tensortrace.net/api/v1/facets'

Responses

StatusMeaningBody type
200Source-backed JSON responseFacetsResponse
400Invalid queryNo declared JSON body
404Unknown model/sourceNo declared JSON body
500Database unavailableNo declared JSON body
503Service temporarily unavailableNo declared JSON body

Response example · 200

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

{
    "models": {
        "providers": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "price_filters": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "capabilities": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "input_modalities": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "output_modalities": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "sorts": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "developers": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "inference_providers": [
            {
                "value": "example",
                "label": "example"
            }
        ]
    },
    "leaderboards": {
        "sources": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "dimensions": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "benchmarks": [
            {
                "value": "example",
                "label": "example"
            }
        ]
    },
    "prices": {
        "sources": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "platforms": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "units": [
            {
                "value": "example",
                "label": "example"
            }
        ]
    },
    "sources": {
        "statuses": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "authorities": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "access_methods": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "freshness": [
            {
                "value": "example",
                "label": "example"
            }
        ]
    }
}
FieldTypeRequiredMeaning / constraints
modelsModelFacetsDtoYes
leaderboardsLeaderboardFacetsDtoYes
pricesPriceFacetsDtoYes
sourcesSourceFacetsDtoYes

Read model filters

GET /api/v1/facets/models

Access: public read; no TensorTrace API key.

Parameters

This operation has no path or query parameters.

Request example

curl 'https://tensortrace.net/api/v1/facets/models'

Responses

StatusMeaningBody type
200Incrementally prepared local dataCatalogFacets
400Invalid queryErrorResponse
404Not present in the prepared catalogErrorResponse
503Catalog preparation has not completed yetErrorResponse

Response example · 200

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

{
    "models": {
        "providers": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "price_filters": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "capabilities": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "input_modalities": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "output_modalities": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "sorts": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "developers": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "inference_providers": [
            {
                "value": "example",
                "label": "example"
            }
        ]
    },
    "model_sources": [
        {
            "value": "example",
            "label": "example"
        }
    ]
}
FieldTypeRequiredMeaning / constraints
modelsModelFacetsDtoYes
model_sourcesarray of objectYes

Only the controls needed by the leaderboards view

GET /api/v1/facets/leaderboards

Access: public read; no TensorTrace API key.

Parameters

This operation has no path or query parameters.

Request example

curl 'https://tensortrace.net/api/v1/facets/leaderboards'

Responses

StatusMeaningBody type
200Source-backed controls, public cache up to 60 secondsobject

Response example · 200

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

{
    "leaderboards": {
        "sources": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "dimensions": [
            {
                "value": "example",
                "label": "example"
            }
        ],
        "benchmarks": [
            {
                "value": "example",
                "label": "example"
            }
        ]
    }
}
FieldTypeRequiredMeaning / constraints
leaderboardsLeaderboardFacetsDtoYes

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