Models
Models are canonical identities, not an inventory of every provider route. Search results are compact cards; the detail endpoint adds overview metadata and counts. Request profiles, specifications and resources separately when you need full detail.
Use source on the profiles section to load one serving source, for example ?source=githubCopilot. The filter is exact and applies before pagination and total_count; other sections reject it. Omit it to read all profiles. Model scores already support their own source filter, and model prices use provider for the serving source.
The default order starts with the highest Intelligence Index, then uses capability scores, ratings and names for deterministic fallbacks. A developer is the author organization; inference_provider is a serving source. Obtain valid filters from Facets. An official ID is preserved independently of the canonical ID and source aliases.
Model classification labels link to the library with model_type, selecting matching primary or secondary classifications before pagination and counts. Use multimodal for MLLM, vlm for image-only VLM, llm for text LLM, or the type ID in another classification link. unknown selects models without source classification or an applicable first-party fallback; omit the filter or use all for all types. Classification uses reported tasks, capabilities and modalities, so a generic multimodal claim alone does not qualify a model as MLLM. Type filters combine with search and organization, capability, modality and price filters.
For a model ID such as google/gemini-2.5-flash, pass google as the publisher segment and gemini-2.5-flash as the model segment. Encode nested slashes in either segment as %2F. Resolved aliases point to the canonical model; unresolved or ambiguous identities are not guessed. The Hugging Face metadata endpoint returns source-native observations rather than card DTOs.
TensorTrace maintains a reviewed first-party knowledge base for missing facts. Generative Llama families without classification evidence default to LLM; explicit source tasks and non-text modality evidence take priority. Applied supplements carry tensortrace_knowledge with registry/rule revisions, the supplemented field and reference URLs. Raw source documents and identities remain unchanged. The same prepared classification is used by type filters and offline catalogs.
On this page
- List and search models ·
GET /models - Read original Hugging Face model metadata ·
GET /huggingface/models - Prepared model overview; expand explicit detail sections as needed ·
GET /models/{provider}/{model} - Complete prepared profiles, specifications or external resources; default 20 per page ·
GET /models/{provider}/{model}/sections/{section} - Read a dated offline client catalog manifest ·
GET /sync/manifest - Download an immutable compressed catalog bucket ·
GET /sync/objects/{hash}
List and search models
GET /api/v1/models
Access: public read; no TensorTrace API key.
Parameters
| Name | Location | Required | Type / limits | Meaning |
|---|---|---|---|---|
q | query | No | string | Case-insensitive search text. Omit it to browse the complete matching catalog. |
query | query | No | string | Alternative spelling of q; when both are supplied, query takes precedence. |
provider | query | No | string | Model publisher namespace. For serving-platform filters, use inference_provider instead. |
source | query | No | string | Registered data-source ID, such as openRouter. This identifies the collecting source, not necessarily the model developer. |
price | query | No | string Default: "all"; Values: all, free, paid | Pricing class: all, free or paid. Uses comparable basic token prices; an unknown price is not free. |
capability | query | No | string | Comma-separated capability identifiers; all must match. |
input_modality | query | No | string | Match an input modality, such as text, image, audio or video. Obtain current values from /facets/models. |
model_type | query | No | string Max. length: 64 | Match a displayed model classification, including secondary types. Use multimodal for MLLM, vlm for image-only VLM, llm for text LLM, or another model type ID from a classification link. unknown selects models without reported classification evidence. Omit or use all for no type filter. Combines with other discovery filters before pagination and counts; an unrecognized ID returns an empty result. |
output_modalities | query | No | string | Comma-separated output modalities; matches models with any listed output modality. all disables this filter. |
sort | query | No | string Default: "intelligence" | Defaults to Intelligence Index descending; unscored models follow using capability, rating and name as deterministic fallbacks. Price sorts use the card-selected USD Input then Output rates, with missing rates last; cache rates do not participate. Tied basic offerings prefer the model developer. Provider-scoped sorts apply the same policy within that source's quotes. |
limit | query | No | integer Default: 48; Minimum: 1; Maximum: 100 | Maximum number of returned rows. The documented default and range apply; numeric pagination limits are clamped unless stated otherwise. |
offset | query | No | integer Default: 0; Minimum: 0 | Zero-based number of matching rows to skip. Default 0; negative values are clamped to 0. |
identity_kind | query | No | string Values: model, family | Restrict identities to a concrete model or a model family; omit to include both. |
developer | query | No | string | Canonical developer ID; groups reviewed publisher aliases. |
inference_provider | query | No | string | Registered inference source ID; selects current source offerings, including price-only records. Adds source-scoped provider_prices; other model fields retain canonical scope. |
Request example
curl 'https://tensortrace.net/api/v1/models?limit=1'
Responses
| Status | Meaning | Body type |
|---|---|---|
200 | Incrementally prepared local data | ModelPage |
400 | Invalid query | ErrorResponse |
404 | Not present in the prepared catalog | ErrorResponse |
503 | Catalog preparation has not completed yet | ErrorResponse |
Response example · 200
Illustrative values; schema-valid and not a live catalog measurement.
{
"data": [
{
"id": "google/gemini-2.5-flash",
"canonical_model_id": "google/gemini-2.5-flash",
"provider": "google",
"name": "Google: Gemini 2.5 Flash",
"official_model_id": "gemini-2.5-flash",
"developer_id": "google",
"developer_name": "Google",
"description": "Illustrative model observation; consult live evidence for current specifications.",
"context_length": 1048576
}
],
"total_count": 1,
"limit": 1,
"offset": 0
}
| Field | Type | Required | Meaning / constraints |
|---|---|---|---|
data | array of CatalogModel | Yes | Max. items: 100 |
total_count | integer | Yes | Minimum: 0 |
limit | integer | Yes | Minimum: 1; Maximum: 100 |
offset | integer | Yes | Minimum: 0 |
Read original Hugging Face model metadata
GET /api/v1/huggingface/models
Access: public read; no TensorTrace API key.
Parameters
| Name | Location | Required | Type / limits | Meaning |
|---|---|---|---|---|
limit | query | No | integer Default: 500; Minimum: 1; Maximum: 1000 | Maximum number of returned rows. The documented default and range apply; numeric pagination limits are clamped unless stated otherwise. |
offset | query | No | integer Default: 0; Minimum: 0 | Zero-based number of matching rows to skip. Default 0; negative values are clamped to 0. |
Request example
curl 'https://tensortrace.net/api/v1/huggingface/models?limit=1'
Responses
| Status | Meaning | Body type |
|---|---|---|
200 | Source-backed JSON response | array of object |
400 | Invalid query | No declared JSON body |
404 | Unknown model/source | No declared JSON body |
500 | Database unavailable | No declared JSON body |
503 | Service temporarily unavailable | No declared JSON body |
Response example · 200
Illustrative values; schema-valid and not a live catalog measurement.
[
{}
]
Type: array of object.
Prepared model overview; expand explicit detail sections as needed
GET /api/v1/models/{provider}/{model}
Access: public read; no TensorTrace API key.
Parameters
| Name | Location | Required | Type / limits | Meaning |
|---|---|---|---|---|
provider | path | Yes | string | Canonical model publisher namespace; URL-encode this path segment. |
model | path | Yes | string | Canonical model name within the publisher namespace. URL-encode nested slashes in this single segment. |
Request example
curl 'https://tensortrace.net/api/v1/models/google/gemini-2.5-flash'
Responses
| Status | Meaning | Body type |
|---|---|---|
200 | Source-backed JSON response | ModelOverview |
400 | Invalid query | No declared JSON body |
404 | Unknown model/source | No declared JSON body |
500 | Database unavailable | No declared JSON body |
503 | Service temporarily unavailable | No declared JSON body |
Response example · 200
Illustrative values; schema-valid and not a live catalog measurement.
{
"canonical_model_id": "google/gemini-2.5-flash",
"model": {
"id": "google/gemini-2.5-flash",
"canonical_model_id": "google/gemini-2.5-flash",
"provider": "google",
"name": "Google: Gemini 2.5 Flash",
"official_model_id": "gemini-2.5-flash",
"developer_id": "google",
"developer_name": "Google",
"description": "Illustrative model observation; consult live evidence for current specifications.",
"context_length": 1048576
},
"capabilities": [
"example"
],
"benchmark_score_counts": {},
"sections": {}
}
| Field | Type | Required | Meaning / constraints |
|---|---|---|---|
canonical_model_id | string | Yes | |
model | CatalogModel | Yes | |
capabilities | array of string | Yes | |
benchmark_score_counts | object | Yes | |
sections | object | Yes | |
references | array of ContentReference | No | Exactly anchored model/distribution metadata. Base-model or derived-from relationships do not establish identity. Max. items: 20 |
Complete prepared profiles, specifications or external resources; default 20 per page
GET /api/v1/models/{provider}/{model}/sections/{section}
Access: public read; no TensorTrace API key.
Parameters
| Name | Location | Required | Type / limits | Meaning |
|---|---|---|---|---|
provider | path | Yes | string | Canonical model publisher namespace; URL-encode this path segment. |
model | path | Yes | string | Canonical model name within the publisher namespace. URL-encode nested slashes in this single segment. |
section | path | Yes | string Values: profiles, specifications, resources | Prepared model section: profiles (platform/generation metadata), specifications (source assertions) or resources (external links). |
source | query | No | string | Exact serving source ID, such as githubCopilot or azureFoundry. Applies to profiles only; other sections reject this filter. Pagination and total_count apply after filtering. Omit to read all platform profiles. |
limit | query | No | integer Default: 20; Minimum: 1; Maximum: 100 | Maximum number of returned rows. The documented default and range apply; numeric pagination limits are clamped unless stated otherwise. |
offset | query | No | integer Default: 0; Minimum: 0 | Zero-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/sections/profiles?limit=1'
Responses
| Status | Meaning | Body type |
|---|---|---|
200 | Current local observations | DetailSectionPage |
400 | Invalid request | No declared JSON body |
404 | Unknown model or section | No declared JSON body |
Response example · 200
Illustrative values; schema-valid and not a live catalog measurement.
{
"data": [
{}
],
"total_count": 1,
"limit": 1,
"offset": 0
}
| Field | Type | Required | Meaning / constraints |
|---|---|---|---|
data | array of object | Yes | Max. items: 100 |
total_count | integer | Yes | Minimum: 0 |
limit | integer | Yes | Minimum: 1; Maximum: 100 |
offset | integer | Yes | Minimum: 0 |
Read a dated offline client catalog manifest
GET /api/v1/sync/manifest
Separate client distribution; ordinary API reads remain current. Compare SHA-256 objects and replace changed buckets. The serial worker publishes at most every 15 minutes. Includes all model cards and organizations plus top 100 entries per core ranking; large llmPerf, Kaggle and historical archive observations remain on-demand. Objects publish before the manifest atomically.
Access: public read; no TensorTrace API key.
Parameters
| Name | Location | Required | Type / limits | Meaning |
|---|---|---|---|---|
If-None-Match | header | No | string | ETag from the last successfully committed local catalog; permits an empty 304 response. |
Request example
curl 'https://tensortrace.net/api/v1/sync/manifest'
Responses
| Status | Meaning | Body type |
|---|---|---|
200 | Offline schema 1 manifest. Hashes cover compressed gzip bytes. | OfflineManifest |
304 | Unchanged manifest; empty body. | No declared JSON body |
503 | No client distribution published yet. | No declared JSON body |
Response example · 200
Illustrative values; schema-valid and not a live catalog measurement.
{
"schema": 1,
"generation": "example",
"generated_at": "2026-10-05T00:00:00Z",
"model_count": 1,
"chunks": [
{
"id": "google/gemini-2.5-flash",
"kind": "models",
"sha256": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
"bytes": 1,
"rows": 1
}
]
}
| Field | Type | Required | Meaning / constraints |
|---|---|---|---|
schema | integer | Yes | |
generation | string | Yes | |
generated_at | string · date-time | Yes | |
model_count | integer | Yes | |
chunks | array of object | Yes |
Download an immutable compressed catalog bucket
GET /api/v1/sync/objects/{hash}
Access: public read; no TensorTrace API key.
Parameters
| Name | Location | Required | Type / limits | Meaning |
|---|---|---|---|---|
hash | path | Yes | string Pattern: ^[0-9a-f]{64}$ | Lowercase SHA-256 from the manifest, covering the compressed object bytes. |
Request example
curl 'https://tensortrace.net/api/v1/sync/objects/EXAMPLE_ID'
Responses
| Status | Meaning | Body type |
|---|---|---|
200 | SHA-256 addressed gzip JSON array. Models: id, model and selectors (search, types, modalities, membership, price and rank), offers. Boards: normalized ranking fields and entries. Metadata: directories and model facets. Validate byte count, hash and manifest row count before a local transaction. Cache-Control: immutable, one year. | string · binary |
404 | Object not found. | No declared JSON body |
Response example · 200
The response contains original bytes or an image. Content types: application/gzip. Preserve the declared encoding and checksum; do not parse it as JSON.