---
title: "Get the system model catalog"
method: GET
path: "/system/admin/model-catalog"
tags: ["系统管理"]
---

# Get the system model catalog

`GET /system/admin/model-catalog`

## Request

- Base URL: `/api/v1` (relative, and the document was published on a file host, not at the API’s origin)
- URL: `/api/v1/system/admin/model-catalog`
- Auth: API key in header `Authorization`

System administrator JWT only; API keys are not accepted. Returns built-in, deployment and effective
catalogs, the current overlay, version/baseline tokens, and the latest 20 published revisions.

## Response `200`

OK

- GithubComTencentWeKnoraInternalApplicationServiceCatalogState
  - `applied_version` integer
  - `baseline` string
  - `builtin` GithubComTencentWeKnoraInternalApplicationServiceCatalogProviderView[]
    - `api` string
    - `id` string
    - `model_thinking_levels` object: ModelThinkingLevels lists, per chat model id, the levels offered once thinking is enabled, resolved against the vendor map and protocol so the console does not re-implement level inheritance.
    - `model_types` GithubComTencentWeKnoraInternalTypesModelType[]
    - `models` GithubComTencentWeKnoraInternalModelsModelSpec[]
      - `aliases` string[]: Aliases are additional ids that resolve to this entry (dated snapshots, vendor-prefixed names on gateways).
      - `api` 'openai-completions' | 'openai-responses' | 'anthropic-messages' | 'google-generative-ai' | 'ollama'
      - `compat` object: Compat is the protocol-specific overlay for this model (flat object, fields depend on API). Decoded lazily by Resolve.
      - `context_window` integer
      - `cost` GithubComTencentWeKnoraInternalModelsModelCost
        - `cache_read` number
        - `cache_write` number
        - `currency` string
        - `input` number
        - `output` number
      - `deprecated` boolean: Deprecated hides the entry from pickers but keeps resolution working.
      - `dimension` integer: Dimension is the embedding vector width (embedding entries only).
      - `id` string
      - `input` string[]: Input lists accepted modalities: text, image, audio, video.
      - `match` string: Match is a case-insensitive glob ("gpt-5*", "*deepseek-r1*") that lets one entry describe a family. Exact ids and aliases win over patterns; among patterns the longest literal prefix wins.
      - `max_output_tokens` integer
      - `name` string
      - `reasoning` boolean: Reasoning reports whether the model can emit thinking at all.
      - `source` string: Source is the documentation URL the facts were taken from.
      - `thinking_levels` GithubComTencentWeKnoraInternalModelsApiThinkingLevelMap
      - `type` 'Embedding' | 'Rerank' | 'KnowledgeQA' | 'VLLM' | 'ASR'
    - `name` string
    - `settings` object
    - `vendor_thinking_levels` GithubComTencentWeKnoraInternalModelsApiReasoningEffort[]: VendorThinkingLevels is what a chat model without its own map offers.
  - `deployment` GithubComTencentWeKnoraInternalApplicationServiceCatalogProviderView[]
    - `api` string
    - `id` string
    - `model_thinking_levels` object: ModelThinkingLevels lists, per chat model id, the levels offered once thinking is enabled, resolved against the vendor map and protocol so the console does not re-implement level inheritance.
    - `model_types` GithubComTencentWeKnoraInternalTypesModelType[]
    - `models` GithubComTencentWeKnoraInternalModelsModelSpec[]
      - `aliases` string[]: Aliases are additional ids that resolve to this entry (dated snapshots, vendor-prefixed names on gateways).
      - `api` 'openai-completions' | 'openai-responses' | 'anthropic-messages' | 'google-generative-ai' | 'ollama'
      - `compat` object: Compat is the protocol-specific overlay for this model (flat object, fields depend on API). Decoded lazily by Resolve.
      - `context_window` integer
      - `cost` GithubComTencentWeKnoraInternalModelsModelCost
        - `cache_read` number
        - `cache_write` number
        - `currency` string
        - `input` number
        - `output` number
      - `deprecated` boolean: Deprecated hides the entry from pickers but keeps resolution working.
      - `dimension` integer: Dimension is the embedding vector width (embedding entries only).
      - `id` string
      - `input` string[]: Input lists accepted modalities: text, image, audio, video.
      - `match` string: Match is a case-insensitive glob ("gpt-5*", "*deepseek-r1*") that lets one entry describe a family. Exact ids and aliases win over patterns; among patterns the longest literal prefix wins.
      - `max_output_tokens` integer
      - `name` string
      - `reasoning` boolean: Reasoning reports whether the model can emit thinking at all.
      - `source` string: Source is the documentation URL the facts were taken from.
      - `thinking_levels` GithubComTencentWeKnoraInternalModelsApiThinkingLevelMap
      - `type` 'Embedding' | 'Rerank' | 'KnowledgeQA' | 'VLLM' | 'ASR'
    - `name` string
    - `settings` object
    - `vendor_thinking_levels` GithubComTencentWeKnoraInternalModelsApiReasoningEffort[]: VendorThinkingLevels is what a chat model without its own map offers.
  - `deployment_error` string
  - `effective` GithubComTencentWeKnoraInternalApplicationServiceCatalogProviderView[]
    - `api` string
    - `id` string
    - `model_thinking_levels` object: ModelThinkingLevels lists, per chat model id, the levels offered once thinking is enabled, resolved against the vendor map and protocol so the console does not re-implement level inheritance.
    - `model_types` GithubComTencentWeKnoraInternalTypesModelType[]
    - `models` GithubComTencentWeKnoraInternalModelsModelSpec[]
      - `aliases` string[]: Aliases are additional ids that resolve to this entry (dated snapshots, vendor-prefixed names on gateways).
      - `api` 'openai-completions' | 'openai-responses' | 'anthropic-messages' | 'google-generative-ai' | 'ollama'
      - `compat` object: Compat is the protocol-specific overlay for this model (flat object, fields depend on API). Decoded lazily by Resolve.
      - `context_window` integer
      - `cost` GithubComTencentWeKnoraInternalModelsModelCost
        - `cache_read` number
        - `cache_write` number
        - `currency` string
        - `input` number
        - `output` number
      - `deprecated` boolean: Deprecated hides the entry from pickers but keeps resolution working.
      - `dimension` integer: Dimension is the embedding vector width (embedding entries only).
      - `id` string
      - `input` string[]: Input lists accepted modalities: text, image, audio, video.
      - `match` string: Match is a case-insensitive glob ("gpt-5*", "*deepseek-r1*") that lets one entry describe a family. Exact ids and aliases win over patterns; among patterns the longest literal prefix wins.
      - `max_output_tokens` integer
      - `name` string
      - `reasoning` boolean: Reasoning reports whether the model can emit thinking at all.
      - `source` string: Source is the documentation URL the facts were taken from.
      - `thinking_levels` GithubComTencentWeKnoraInternalModelsApiThinkingLevelMap
      - `type` 'Embedding' | 'Rerank' | 'KnowledgeQA' | 'VLLM' | 'ASR'
    - `name` string
    - `settings` object
    - `vendor_thinking_levels` GithubComTencentWeKnoraInternalModelsApiReasoningEffort[]: VendorThinkingLevels is what a chat model without its own map offers.
  - `history` GithubComTencentWeKnoraInternalApplicationServiceCatalogRevision[]
    - `overlay` object
    - `updated_at` string
    - `updated_by` string
    - `version` integer
  - `overlay` object
  - `sync_error` string
  - `version` integer

## Other responses

- `401`: Unauthorized
- `403`: Forbidden
- `503`: Service Unavailable

## Changes

- **2026-10-14** `a1c41ab134cc`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/tencentblueking/apis/weknora-api/changes/system/admin/model-catalog/get.md)

---

[API](https://skmtc.dev/tencentblueking/apis/weknora-api.md) - [All operations](https://skmtc.dev/tencentblueking/apis/weknora-api/llms.txt) - [OpenAPI document](https://skmtc.dev/tencentblueking/apis/weknora-api/revisions/685d1f9fce30?raw)