> ## Documentation Index > Fetch the complete documentation index at: https://www.c1.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # List Inference Catalog > ListInferenceCatalog returns the providers, variants and suggested models that inference routes can be built from, C1's registered models by family, and the model each C1 tier uses for the caller's tenant. The Edge feature is required. ## OpenAPI ````yaml https://spec.speakeasy.com/conductor-one/conductorone/my-source-with-code-samples get /api/v1/edges/inference/catalog openapi: 3.1.0 info: description: The C1 API is a HTTP API for managing C1 resources. title: C1 API version: 0.1.0-alpha servers: - description: The C1 API server for the current tenant. url: https://{tenantDomain}.conductor.one variables: tenantDomain: default: example description: The domain of the tenant to use for this request. security: - bearerAuth: [] oauth: [] paths: /api/v1/edges/inference/catalog: get: tags: - Edge summary: List Inference Catalog description: >- ListInferenceCatalog returns the providers, variants and suggested models that inference routes can be built from, C1's registered models by family, and the model each C1 tier uses for the caller's tenant. The Edge feature is required. operationId: c1.api.edge.v1.EdgeService.ListInferenceCatalog responses: '200': content: application/json: schema: $ref: >- #/components/schemas/c1.api.edge.v1.EdgeServiceListInferenceCatalogResponse description: >- EdgeServiceListInferenceCatalogResponse contains every catalog entry. components: schemas: c1.api.edge.v1.EdgeServiceListInferenceCatalogResponse: description: EdgeServiceListInferenceCatalogResponse contains every catalog entry. properties: capabilitySummary: oneOf: - $ref: '#/components/schemas/c1.api.edge.v1.EdgeCapabilitySummary' - type: 'null' entries: description: The entries field. items: $ref: '#/components/schemas/c1.api.edge.v1.EdgeInferenceCatalogEntry' type: - array - 'null' families: description: >- C1's registered models grouped by family, with the ways an Edge can serve each. items: $ref: '#/components/schemas/c1.api.edge.v1.EdgeInferenceModelFamily' type: - array - 'null' tiers: description: >- The model each C1 tier currently uses for the caller's tenant. A tier with no model is left out. items: $ref: '#/components/schemas/c1.api.edge.v1.EdgeInferenceTierOption' type: - array - 'null' title: Edge Service List Inference Catalog Response type: object x-speakeasy-name-override: EdgeServiceListInferenceCatalogResponse c1.api.edge.v1.EdgeCapabilitySummary: description: >- EdgeCapabilitySummary describes the capability reports of a tenant's connected Edge processes. properties: lastReportedAt: format: date-time type: - string - 'null' reportingProcesses: description: Edge processes with a live report. format: uint32 type: integer title: Edge Capability Summary type: object x-speakeasy-name-override: EdgeCapabilitySummary c1.api.edge.v1.EdgeInferenceCatalogEntry: description: >- EdgeInferenceCatalogEntry is a provider that Edge inference routes can target. properties: channel: description: Release channel; higher values are less stable. enum: - MCP_SERVER_CATALOG_CHANNEL_UNSPECIFIED - MCP_SERVER_CATALOG_CHANNEL_STABLE - MCP_SERVER_CATALOG_CHANNEL_BETA - MCP_SERVER_CATALOG_CHANNEL_ALPHA type: string x-speakeasy-unknown-values: allow credentialKind: description: The credentialKind field. enum: - EDGE_INFERENCE_CATALOG_CREDENTIAL_KIND_UNSPECIFIED - EDGE_INFERENCE_CATALOG_CREDENTIAL_KIND_API_KEY - >- EDGE_INFERENCE_CATALOG_CREDENTIAL_KIND_AWS_WORKLOAD_IDENTITY_REGION type: string x-speakeasy-unknown-values: allow displayName: description: The displayName field. type: string iconKey: description: Key the client maps to a provider icon. type: string id: description: Entry identifier. type: string secretContentType: description: Content type the credential secret must have for API key entries. type: string variants: description: The variants field. items: $ref: '#/components/schemas/c1.api.edge.v1.EdgeInferenceCatalogVariant' type: - array - 'null' title: Edge Inference Catalog Entry type: object x-speakeasy-name-override: EdgeInferenceCatalogEntry c1.api.edge.v1.EdgeInferenceModelFamily: description: EdgeInferenceModelFamily groups registered models, e.g. "Claude Opus". properties: family: description: >- Family name; models with no family are grouped under their own display name. type: string models: description: The models field. items: $ref: '#/components/schemas/c1.api.edge.v1.EdgeInferenceRegistryModel' type: - array - 'null' title: Edge Inference Model Family type: object x-speakeasy-name-override: EdgeInferenceModelFamily c1.api.edge.v1.EdgeInferenceTierOption: description: >- EdgeInferenceTierOption is a C1 tier and the model it uses for the caller's tenant. properties: aliasRouteId: description: Route id published as the model alias. type: string modelDisplayName: description: The modelDisplayName field. type: string modelId: description: Registry model id the tier uses. type: string routeId: description: Route id published for the tier, e.g. c1-fast. type: string tier: description: The tier field. enum: - EDGE_INFERENCE_TIER_UNSPECIFIED - EDGE_INFERENCE_TIER_FAST - EDGE_INFERENCE_TIER_BALANCED - EDGE_INFERENCE_TIER_BEST type: string x-speakeasy-unknown-values: allow title: Edge Inference Tier Option type: object x-speakeasy-name-override: EdgeInferenceTierOption c1.api.edge.v1.EdgeInferenceCatalogVariant: description: >- EdgeInferenceCatalogVariant is one way to reach a provider: a provider profile with its native format, destination, credential source and model id grammar. properties: availabilityWarning: description: >- Set when only some connected Edge processes can serve the variant, as during a rollout. type: string credentialRecipe: description: Credential recipe for AWS variants; empty otherwise. type: string credentialSource: description: The credentialSource field. enum: - EDGE_INFERENCE_CREDENTIAL_SOURCE_UNSPECIFIED - EDGE_INFERENCE_CREDENTIAL_SOURCE_TENANT_VAULT - EDGE_INFERENCE_CREDENTIAL_SOURCE_AWS_WORKLOAD_IDENTITY type: string x-speakeasy-unknown-values: allow defaultSupportedReasoningEfforts: description: >- Reasoning effort levels assumed for a model id that is not suggested, lowest first. Empty means unknown. items: type: string type: - array - 'null' destination: description: >- Destination written to the target. AWS variants use a template with {region}. type: string displayName: description: Human-readable variant name. type: string id: description: Variant identifier, unique within its entry. type: string modelHint: description: >- Placeholder describing the accepted model id shape, for the free-text field. type: string modelIdGrammar: description: The modelIdGrammar field. type: string nativeFormat: description: Client format the variant serves. enum: - EDGE_INFERENCE_NATIVE_FORMAT_UNSPECIFIED - EDGE_INFERENCE_NATIVE_FORMAT_OPENAI_RESPONSES - EDGE_INFERENCE_NATIVE_FORMAT_OPENAI_CHAT - EDGE_INFERENCE_NATIVE_FORMAT_ANTHROPIC_MESSAGES type: string x-speakeasy-unknown-values: allow providerProfile: description: Provider profile written to the target. type: string suggestedModels: description: The suggestedModels field. items: $ref: '#/components/schemas/c1.api.edge.v1.EdgeInferenceCatalogModel' type: - array - 'null' unavailable: description: >- True when every Edge process this tenant has connected has reported that it cannot serve this variant. False, including when no Edge has reported, means the variant is offered as before. Region-scoped variants are not gated here because the region is chosen later. type: boolean unavailableReason: description: Why the variant is unavailable. Set only with unavailable. type: string upstreamPath: description: The upstreamPath field. type: string title: Edge Inference Catalog Variant type: object x-speakeasy-name-override: EdgeInferenceCatalogVariant c1.api.edge.v1.EdgeInferenceRegistryModel: description: EdgeInferenceRegistryModel is a model C1 has registered for use. properties: contextWindowTokens: description: Zero when unknown. format: uint32 type: integer displayName: description: The displayName field. type: string modelId: description: Registry model id, written to EdgeInferenceRoute.registry_model_id. type: string routeId: description: 'Suggested route id: the model''s name in route id form.' type: string serveOptions: description: Ways to serve the model, in C1's preferred order. items: $ref: '#/components/schemas/c1.api.edge.v1.EdgeInferenceServeOption' type: - array - 'null' title: Edge Inference Registry Model type: object x-speakeasy-name-override: EdgeInferenceRegistryModel c1.api.edge.v1.EdgeInferenceCatalogModel: description: >- EdgeInferenceCatalogModel is a suggested upstream model. Suggestions are not exhaustive: any model id the variant's grammar accepts can be used. properties: displayName: description: Human-readable model name. type: string id: description: Upstream model id to send. type: string supportedReasoningEfforts: description: >- Reasoning effort levels the model accepts (`none`, `minimal`, `low`, `medium`, `high`), lowest first. Empty means C1 does not know, so any level may be offered. items: type: string type: - array - 'null' title: Edge Inference Catalog Model type: object x-speakeasy-name-override: EdgeInferenceCatalogModel c1.api.edge.v1.EdgeInferenceServeOption: description: >- EdgeInferenceServeOption is one way an Edge can serve a registered model: a catalog variant and the exact upstream model id to send through it. properties: catalogEntryId: description: Catalog entry (provider) id. type: string catalogVariantId: description: Catalog variant id within the entry. type: string nativeFormat: description: Client format the option serves. enum: - EDGE_INFERENCE_NATIVE_FORMAT_UNSPECIFIED - EDGE_INFERENCE_NATIVE_FORMAT_OPENAI_RESPONSES - EDGE_INFERENCE_NATIVE_FORMAT_OPENAI_CHAT - EDGE_INFERENCE_NATIVE_FORMAT_ANTHROPIC_MESSAGES type: string x-speakeasy-unknown-values: allow region: description: AWS region the target uses; empty for API-key providers. type: string upstreamModelId: description: Upstream model id to send. type: string title: Edge Inference Serve Option type: object x-speakeasy-name-override: EdgeInferenceServeOption securitySchemes: bearerAuth: scheme: bearer type: http oauth: description: >- This API uses OAuth2 with the Client Credential flow. Client Credentials must be sent in the BODY, not the headers. For an example of how to implement this, refer to the [c1TokenSource.Token()](https://github.com/ConductorOne/conductorone-sdk-go/blob/3375fe7c0126d17e7ec4e711693dee7b791023aa/token_source.go#L101-L187) function. flows: clientCredentials: scopes: {} tokenUrl: /auth/v1/token type: oauth2 ````