> ## Documentation Index > Fetch the complete documentation index at: https://docs.prisme.ai/llms.txt > Use this file to discover all available pages before exploring further. # List models from the catalogue > Returns a paginated, filterable list of models from the gateway catalogue. **Note.** The response uses Prisme.ai's standard pagination envelope (`{ items, total, page, limit }`), **not** OpenAI's `{ object: "list", data: [...] }` shape - this endpoint is the management catalogue, not the OpenAI-compatible model listing. Per-org availability filter: - No `orgSlug` query → restrict to models reachable from the current session (no `org_slugs` constraint, or the session's org is listed). - `orgSlug=all` (admin only) → returns the full catalogue regardless of per-model `org_slugs`. - `orgSlug=` (admin only) → impersonate that org's view. ## OpenAPI ````yaml /api-reference/llm-gateway/swagger.yml get /v1/models openapi: 3.0.3 info: version: 1.0.0 title: LLM Gateway API description: | Public REST API for the Prisme.ai LLM Gateway - OpenAI-compatible chat completions and embeddings, plus a managed model catalogue with governance overrides per organization. The gateway abstracts multi-provider LLM access (OpenAI, Azure OpenAI, Anthropic, Google Vertex, AWS Bedrock, OpenAI-compatible providers) behind an OpenAI-compatible request/response shape. It enforces per-tenant governance (allowed models, default models, quotas) and emits analytics events (`analytics.llm.completion`) usable for cost and carbon reporting. This spec documents only the public REST surface (endpoints exposed via Prisme.ai workspace webhooks). Internal helpers (private automations prefixed with `_`) and load-test mocks are not part of the public contract. contact: name: Prisme.ai url: https://prisme.ai servers: - url: https://{host}/v2/workspaces/slug:llm-gateway/webhooks description: Prisme.ai workspace webhooks variables: host: default: api.studio.prisme.ai description: API host (override for self-hosted or sandbox) security: - BearerAuth: [] - OrgApiKeyAuth: [] tags: - name: Completions description: OpenAI-compatible chat completions (with optional SSE streaming). - name: Embeddings description: OpenAI-compatible text embeddings. - name: Models description: Model catalogue (CRUD + bulk replace + governance-aware listing). - name: Defaults description: >- Resolved default models for completions / embeddings / image generation / file parsing. - name: Test description: Smoke-test reachability of a model through the gateway. paths: /v1/models: get: tags: - Models summary: List models from the catalogue description: | Returns a paginated, filterable list of models from the gateway catalogue. **Note.** The response uses Prisme.ai's standard pagination envelope (`{ items, total, page, limit }`), **not** OpenAI's `{ object: "list", data: [...] }` shape - this endpoint is the management catalogue, not the OpenAI-compatible model listing. Per-org availability filter: - No `orgSlug` query → restrict to models reachable from the current session (no `org_slugs` constraint, or the session's org is listed). - `orgSlug=all` (admin only) → returns the full catalogue regardless of per-model `org_slugs`. - `orgSlug=` (admin only) → impersonate that org's view. operationId: listModels parameters: - in: query name: limit schema: type: string description: Page size (capped server-side at 100, default 100). - in: query name: page schema: type: string description: Zero-based page index. - in: query name: type schema: type: string enum: - completion - embeddings - image_generation description: Filter by model type. - in: query name: enabled schema: type: string enum: - 'true' - 'false' description: Filter by enabled flag. - in: query name: model_ids schema: type: string description: Comma-separated list of model IDs. - in: query name: tags schema: type: string description: Comma-separated list of tags (matches any). - in: query name: visible_only schema: type: string enum: - 'true' - 'false' description: When `"true"`, exclude models with `display.hidden = true`. - in: query name: brand schema: type: string description: Exact match on `display.brand`. - in: query name: search schema: type: string description: >- Case-insensitive search across `model_id`, `display.name`, `display.brand`. - in: query name: capability schema: type: string enum: - vision - audio - text - image description: Filter to models declaring the given capability. - in: query name: orgSlug schema: type: string description: | Admin-only override for the per-org availability filter. Use `all` to bypass the filter, or a slug to impersonate that org's view. Ignored for non-admin callers. responses: '200': description: Paginated list of models. content: application/json: schema: $ref: '#/components/schemas/ModelsListResponse' '401': description: Missing or invalid authentication. content: application/json: schema: $ref: '#/components/schemas/Error' '405': description: Method not allowed. content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: ModelsListResponse: type: object description: | Pagination envelope used by `GET /v1/models` (Prisme.ai standard, not OpenAI's `{ object: "list", data: [...] }`). required: - items - total - page - limit properties: items: type: array items: $ref: '#/components/schemas/Model' total: type: integer description: Total number of matching documents (ignoring pagination). page: type: integer description: Zero-based page index. limit: type: integer description: Effective page size (server-capped at 100). Error: type: object required: - error description: | Standard error envelope. `error` carries either a stable PascalCase identifier or a free-text label (legacy endpoints) - `code` is the canonical machine-readable identifier going forward. properties: error: type: string description: Stable PascalCase identifier or short error label. message: type: string description: Human-readable error message. code: type: string description: | Machine-readable error code. Observed values include `RATE_LIMITED`, `MODEL_NOT_ALLOWED`, `MODEL_NOT_FOUND`, `MODEL_EXISTS`, `MISSING_MODEL_ID`, `MISSING_TYPE`, `INVALID_BODY`, `INVALID_ITEMS`, `INVALID_DIMENSIONS`, `PAYLOAD_TOO_LARGE`, `METHOD_NOT_ALLOWED`, `PROVIDER_ERROR`, `PROVIDER_NO_RESPONSE`. details: description: Optional structured context (e.g. list of invalid items). additionalProperties: true status: type: integer description: HTTP status mirror, when present. retryAfter: type: integer description: Seconds to wait before retrying (rate-limit responses). provider: type: string description: Upstream provider name (provider-error responses). model: type: string description: Model id involved in the error (provider-error responses). provider_error_type: type: string description: Upstream provider's own error class name. Model: type: object description: | Model catalogue document. The catalogue is the source of truth for provider routing, capabilities, pricing, and per-org availability. required: - model_id - type properties: model_id: type: string maxLength: 128 description: Stable identifier (matches the value sent in `request.model`). type: type: string maxLength: 64 enum: - completion - embeddings - image_generation description: Model family. display: type: object description: Display metadata (label, brand, hidden flag). properties: name: type: string brand: type: string hidden: type: boolean capabilities: type: object description: Flags advertising what the model supports. properties: vision: type: boolean audio: type: boolean text: type: boolean image: type: boolean limits: type: object description: Provider-side limits (e.g. context window, max tokens). additionalProperties: true failover: type: string maxLength: 128 description: Optional `model_id` to route to when the primary fails. region: type: string maxLength: 64 description: Hosting region (free-text). dimensions: description: Default embedding dimensionality (embeddings models only). supported_dimensions: type: array description: Allowed values for the request `dimensions` parameter. items: type: number metrics: description: Free-form metrics block (latency, throughput hints, …). provider_config: type: object description: Provider-specific configuration (batch size, parallelism, …). additionalProperties: true pricing: type: object description: Cost configuration used to compute `usage.cost`. properties: input_per_1m_tokens: type: number format: double output_per_1m_tokens: type: number format: double tags: type: array description: Free-form tags used by the search/filter UI. items: type: string org_slugs: type: array description: | When set and non-empty, restricts the model to the listed organizations. Empty / missing means the model is available to all orgs (subject to governance overlays). items: type: string enabled: type: boolean description: When `false`, the model is hidden from routing. securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: | User-bound credential carrying an identity: either a session JWT or a user access token (`at:*`) generated from the user settings UI. Send as `Authorization: Bearer `. Org API keys (`iak_*`) are **not** accepted here - they carry no user identity. Use the `x-prismeai-api-key` header instead (see `OrgApiKeyAuth`). OrgApiKeyAuth: type: apiKey in: header name: x-prismeai-api-key description: | Organization API key (`iak_{orgSlug}_{uuid}`). Unlike `Authorization: Bearer`, this credential is **not** tied to a user identity - it is bound to the org and its effective access is defined by the scopes / permission rules attached to it (it can be restricted to a single project, or kept broader). Send as `x-prismeai-api-key: iak_...`. ````