Get Available Model Catalog
Retrieve all models, providers, and default model IDs available to the caller with optional version caching and custom sorting.
Endpoint Overview
- Method :
GET - Path :
/api/core/ai/model/catalog - Module : Core Features / Models
- Authentication :
Authorization: Bearer <apiKey>—Personal API Key (access scoped by team member permissions) (see API Getting Started ) - Interactive Try-It-Out : Open in Scalar API Explorer (self-hosted instances: replace the origin with
<instance>/apidoc/systemopenapi#tag/%E6%A8%A1%E5%9E%8B%E7%AE%A1%E7%90%86/GET/core/ai/model/catalog)
Description & Notes
Returns available models, providers, and effective default model IDs for the authenticated member or share-link identity in a single request, with content version negotiation. Passing orderBy=custom orders by own team models, shared team models, and system models sorted by rank ; omitting preserves runtime order. Members may pass includeSourceMember=true to attach creator details (always returning the full catalog; ignored for share links).
Request Parameters
Query Parameters
| Field | Type | Required | Default | Constraints & Description |
|---|---|---|---|---|
version | string | No | - | Client-cached catalog version hash. minLength: 1 |
includeSourceMember | boolean | No | - | Attach source member metadata (members only; always returns the full catalog without version cache) |
orderBy | "custom" | No | - | Catalog display sorting: custom orders own team, shared team, and system models by rank; omit to keep runtime order. Fixed: "custom" |
outLinkAuthData | string | No | - | Share-link auth payload used to evaluate permissions via the link publisher identity |
Request Examples
Replace YOUR_API_KEY and placeholder IDs before running. Self-hosted users should replace the base URL with <instance>/api .
cURL Example
curl --fail-with-body -X GET "https://cloud.fastgpt.io/api/core/ai/model/catalog" \
-H "Authorization: Bearer YOUR_API_KEY"Response Schema & Examples
Successful /api/* calls return the standard FastGPT envelope { "code": 200, "statusText": "", "message": "", "data": ... } , where data matches the 200 schema below (when a payload schema is declared; otherwise refer to the status description for runtime data semantics).
HTTP 200
Returns the full catalog when the version changes or includeSourceMember=true ; otherwise returns only version
Content-Type : application/json
| Field | Type | Required | Default | Constraints & Description |
|---|---|---|---|---|
version | string | Yes | - | Current model catalog version hash |
data | object | No | - | Full catalog payload (omitted when client version matches and creator details are not requested) |
data.models | object[] | Yes | - | - |
data.providers | object[] | Yes | - | - |
data.providers[].provider | string | Yes | - | Model provider identifier |
data.providers[].value | object | Yes | - | - |
data.providers[].value.en | string | Yes | - | - |
data.providers[].value.zh-CN | string | Yes | - | - |
data.providers[].value.zh-Hant | string | Yes | - | - |
data.providers[].avatar | string | Yes | - | Model provider icon URL |
data.defaultModelIds | object | Yes | - | - |
data.defaultModelIds.llm | string | No | - | - |
data.defaultModelIds.embedding | string | No | - | - |
data.defaultModelIds.tts | string | No | - | - |
data.defaultModelIds.stt | string | No | - | - |
data.defaultModelIds.rerank | string | No | - | - |
data.defaultModelIds.datasetTextLLM | string | No | - | - |
data.defaultModelIds.datasetImageLLM | string | No | - | - |
data.defaultModelIds.chatTitleLLM | string | No | - | - |
Last updated