SnozeDevelopers
API referenceAi

Read published models and routing

Public, workspace-independent configuration shared by attachment checks and execution. Disabled models are omitted.

GET
/v1/ai/model-catalog

Response Body

Success

application/json
  1. response
data*
Example Request
curl -X GET 'https://api.snoze.dev/v1/ai/model-catalog'
Example Response
{  "data": {    "models": [      {        "id": "string",        "label": "string",        "icon": "string",        "group": "frontier",        "vision": true,        "documents": true,        "maxImageBytes": 0,        "video": true,        "audio": true,        "disabled": true,        "costX": 0,        "description": "string",        "speed": 0,        "intelligence": 0,        "effortLevels": [          "minimal"        ],        "tier": "A",        "minPlan": "free",        "metadata": {          "inputModalities": [            "string"          ],          "outputModalities": [            "string"          ],          "supportedParameters": [            "string"          ],          "reasoning": {            "mandatory": true,            "supportedEfforts": [              "string"            ],            "defaultEffort": "string",            "defaultEnabled": true          },          "contextLength": 0,          "maxOutputTokens": 0,          "pricing": {            "prompt": "string",            "completion": "string",            "inputCacheRead": "string",            "inputCacheWrite": "string",            "request": "string",            "tiers": [              {                "minPromptTokens": 0,                "prompt": "string",                "completion": "string",                "inputCacheRead": "string",                "inputCacheWrite": "string"              }            ]          },          "created": 0,          "expirationDate": "string",          "canonicalSlug": "string"        }      }    ],    "routes": {      "policies": {        "agent.fast": "string",        "agent.strong": "string",        "structured.fast": "string",        "structured.strong": "string"      },      "autoLadder": [        "string"      ],      "autoModelByPlan": {        "free": "string",        "team": "string",        "business": "string",        "enterprise": "string"      },      "onboarding": "string"    },    "revision": 0,    "updatedAt": "string"  }}

Run a cited semantic search over a chat's sources

Embeds the query and returns the closest chunks with similarity scores and stable, human-readable citations, restricted to the chat's selected sources (or the whole workspace when none are selected) and filtered again by the caller's per-source access. Requires a workspace member with the `ai:read` permission and a plan that includes the `semantic_search` feature; a workspace without it is refused as entitlement-locked. Pass `limit` to cap the number of results.

List the featured AI models

Returns enabled models from the published admin catalog, with display, capability, and minimum-plan configuration. Public and workspace-independent.