> ## Documentation Index > Fetch the complete documentation index at: https://docs.cognigy.com/llms.txt > Use this file to discover all available pages before exploring further. # Get large language models > Gets [large language models](https://docs.cognigy.com/ai/agents/develop/gen-ai-and-llms/llms) in a Project. By default, 25 large language models are returned. To change this value, use the `limit` query parameter. Additionally, you can filter, sort, and paginate the results. ## OpenAPI ````yaml https://api-trial.cognigy.ai/openapi/openapi-viewer.json get /v2.0/largelanguagemodels openapi: 3.0.0 info: title: Cognigy.AI REST-ful-API Reference version: 2026.10.0 description: > ### Introduction This is the [OpenAPI 3.0](https://swagger.io/specification/) documentation of the [REST](https://en.wikipedia.org/wiki/Representational_state_transfer)-ful Cognigy.AI API. ### Cross-Origin Resource Sharing This API features Cross-Origin Resource Sharing (CORS) implemented in compliance with [W3C spec](https://www.w3.org/TR/cors/), which allows cross-domain communication from the browser. All responses include a wildcard same-origin header, making the API fully accessible. ### Authentication Cognigy.AI offers four forms of authentication: - API Key - CXone Token - OAuth2 - BasicAuth An API Key is a security token. You can use API Keys in your path or HTTP header. Never expose your API Key and keep it safe and secure. Revoke the API Key if it got exposed or stolen. OAuth2 is an open protocol to allow secure authorization by web, mobile and desktop applications. For further information see [RFC 6749 - "The OAuth 2.0 Authorization Framework"](https://tools.ietf.org/html/rfc6749) and [RFC 6750 - "The OAuth 2.0 Authorization Framework: Bearer Token Usage"](https://tools.ietf.org/html/rfc6750). Basic Auth is only used for API calls regarding the Management-UI. ### Error Handling This API uses HTTP status codes equal or above 400 to indicate errors. Error details are generated in compliance with [RFC 7807 - "Problem Details for HTTP APIs"](https://tools.ietf.org/html/rfc7807). Every error response contains a traceId, which should be provided to the Cognigy.AI Technical Support when reporting an error. contact: name: Cognigy Technical Support url: https://www.cognigy.com email: support@cognigy.com servers: - url: https://api-trial.cognigy.ai/new/ description: Cognigy.AI API security: - APIKeyHeader: [] - APIKeyQueryParam: [] - CXoneTokenHeader: [] - OAuth2: [] - BasicAuth: [] tags: - name: Cognigy.AI REST-ful API description: The Cognigy.AI REST-ful API externalDocs: description: Cognigy.AI Documentation url: https://docs.cognigy.com/docs/ paths: /v2.0/largelanguagemodels: get: tags: - Large Language Models summary: Get large language models description: >- Gets [large language models](https://docs.cognigy.com/ai/agents/develop/gen-ai-and-llms/llms) in a Project. By default, 25 large language models are returned. To change this value, use the `limit` query parameter. Additionally, you can filter, sort, and paginate the results. operationId: indexLargeLanguageModels_2_0 parameters: - in: header name: Accept description: >- The `Accept` header specifies the media type that the client expects in the response. Available options: `application/json`, `application/hal+json`, `application/xml`, `text/xml`, `text/csv`. The default value is `application/json`. required: false schema: type: string enum: - application/json - application/hal+json - application/xml - text/xml - text/csv example: application/json - in: query name: projectId description: The unique identifier for the Project. required: false schema: type: string pattern: ^[a-z0-9]{24}$ minLength: 24 maxLength: 24 - in: query name: filter required: false schema: type: string description: Filter records by specific field eg:name. - in: query name: limit required: false schema: type: integer minimum: 1 maximum: 100 description: >- The maximum number of items to return. Use this parameter to control page size. The default value is 25, and the maximum permitted value is 100. - in: query name: skip required: false schema: type: integer minimum: 0 description: >- The number of items to skip before returning the results. Use this parameter with `limit` for offset-based pagination. The default value is 0. - in: query name: sort required: false schema: type: string minLength: 1 description: >- The order in which results are returned. Set a sorting rule in the format `field:direction`, where direction can be `asc` for ascending order or `desc` for descending order. For example, `name:asc` sorts by name in ascending order. - in: query name: next required: false schema: type: string minLength: 24 maxLength: 24 description: >- The cursor that points to the next page of results. Use the `nextCursor` value returned in a previous response to request the next set of items. - in: query name: previous required: false schema: type: string minLength: 24 maxLength: 24 description: >- The cursor that points to the previous page of results. Use the `previousCursor` value returned in a previous response to request the previous set of items. - in: query name: resourceLevel description: Scope of the resource (global "organisation" or project). required: false schema: type: string enum: - organisation - project description: General scope of the resource. default: project responses: '200': description: Returns array of large language model metadata objects. content: application/json: schema: type: object properties: items: type: array items: type: object oneOf: - type: object required: - name - modelType - provider - connectionId properties: name: type: string example: Large language model for customer service description: type: string example: >- Large language model for customer-facing AI Agents. modelType: type: string enum: - gpt-3.5-turbo - gpt-3.5-turbo-instruct - gpt-4 - gpt-4o - gpt-4o-mini - gpt-4.1 - gpt-4.1-mini - gpt-4.1-nano - gpt-5 - gpt-5-nano - gpt-5-mini - gpt-5.4-mini - gpt-5.4-nano - gpt-5-chat-latest - gpt-5.1 - gpt-5.2 - gpt-5.4 - gpt-5.5 - text-embedding-ada-002 - luminous-extended-control - luminous-embedding-128 - Pharia-1-Embedding-4608 - gemini-embedding-001 - claude-3-opus-20240229 - claude-sonnet-4-6 - custom-model - custom-embedding-model - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-3.1-pro-preview - gemini-3-flash-preview - gemini-3.1-flash-lite-preview - mistral-large-2411 - mistral-small-2503 - pixtral-large-2411 - pixtral-12b-2409 modelGroup: type: string enum: - chat - completion - embedding apiType: type: string enum: - chatCompletion - responses description: >- The API type for chat models. Defaults to chatCompletion when not specified. The responses API is only supported for OpenAI, Azure OpenAI, and OpenAI Compatible providers. isCustomModel: type: boolean example: true provider: type: string enum: - azureOpenAI - openAI - anthropic - googleVertexAI - googleGemini - googleGenAI - alephAlpha - awsBedrock - mistral connectionId: type: string format: uuid minLength: 36 maxLength: 36 description: >- The identifier for the large language model connection. openAI: type: object description: Metadata for OpenAI large language models. properties: customModel: type: string example: gpt-4-32k-0613 description: The custom model name. anthropic: type: object description: Metadata for Anthropic large language models. properties: customModel: type: string example: claude-opus-4-0 description: The custom model name. azureOpenAI: type: object description: Metadata for Azure OpenAI large language models. properties: resourceName: type: string description: >- The Azure OpenAI resource name. For more information, read the [Microsoft Azure OpenAI resource](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/create-resource?pivots=web-portal#create-a-resource) documentation. deploymentName: type: string description: >- The model deployment name. For more information, read the [Microsoft Azure OpenAI resource](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/create-resource?pivots=web-portal#deploy-a-model) documentation. apiVersion: type: string description: >- The API version in `YYYY-MM-DD` format (for example, `YYYY-MM-DD-preview`). For more information, read the [Microsoft Azure OpenAI REST API versioning](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/reference#rest-api-versioning) documentation. baseCustomUrl: type: string description: >- The custom URL to route connections between your clusters and Microsoft Azure OpenAI through a dedicated proxy for enhanced security. When set, `resourceName`, `deploymentName`, and `apiVersion` are ignored. For API key connections on 2025.20 and earlier use `https://.openai.azure.com/openai/deployments//?api-version=`. example: - >- https://.openai.azure.com/openai/deployments//chat/completions?api-version= - >- https://.openai.azure.com/openai/deployments//completions?api-version= - >- https://.openai.azure.com/openai/deployments//embeddings?api-version= googleVertexAI: type: object description: >- Metadata for Google Vertex AI large language models. properties: location: type: string apiEndpoint: type: string publisher: type: string googleGemini: type: object description: >- Metadata for Google Gemini large language models. properties: location: type: string googleGenAI: type: object description: Google GenAI specific meta data properties: location: type: string alephAlpha: type: object description: Metadata for Aleph Alpha large language models. properties: customModel: type: string example: luminous-003 description: The custom model name. baseCustomUrl: type: string example: https://api.aleph-alpha.com openAICompatible: type: object description: >- Metadata for OpenAI-compatible large language models. properties: customModel: type: string example: luminous-003 description: The custom model name. baseCustomUrl: type: string example: >- https://own-llm-deployment.company.com/openai/v1 customAuthHeader: type: string example: Ocp-Apim-Subscription-Key description: >- The API key will be sent via this http header if specified. resourceLevel: type: string enum: - project description: Scope for project-level resources. isDefault: type: boolean description: >- If set to `true`, the large language model is used as the default large language model when no other large language model is set. example: false fallbacks: type: array description: >- (Alpha) The list of fallback large language models used when the primary large language model stops working. items: type: object properties: isFallbackEnabled: type: boolean description: >- If set to `true`, activates large language model fallback. fallbackLLMReferenceId: type: string format: uuid minLength: 36 maxLength: 36 description: >- The identifier for the fallback large language model. immediateFallBack: type: object properties: failedRequests: type: number description: >- The number of failed requests until the fallback large language model is used instead of the primary large language model. durationInMinutes: type: number description: >- The duration in minutes for which the fallback large language model is used instead of the primary large language model. emailNotificationList: type: array items: type: string description: >- The list of email addresses to notify when the large language model fallback is triggered. description: Large language model fallback configuration. referenceId: type: string description: The reference ID of the large language model. format: uuid _id: type: string pattern: ^[a-z0-9]{24}$ minLength: 24 maxLength: 24 createdAt: type: integer description: Unix-timestamp example: 1694518620 minimum: 0 maximum: 2147483647 lastChanged: type: integer description: Unix-timestamp example: 1694518620 minimum: 0 maximum: 2147483647 createdBy: type: string pattern: ^[a-z0-9]{24}$ minLength: 24 maxLength: 24 lastChangedBy: type: string pattern: ^[a-z0-9]{24}$ minLength: 24 maxLength: 24 description: > The IEntityMeta defines meta information every entity within the system has. These are dates when a resource was created and modified as well as information about the user who initially created a resource and who modified it the last time. - type: object required: - name - modelType - provider - connectionId - resourceLevel properties: name: type: string example: Large language model for customer service description: type: string example: >- Large language model for customer-facing AI Agents. modelType: type: string enum: - gpt-3.5-turbo - gpt-3.5-turbo-instruct - gpt-4 - gpt-4o - gpt-4o-mini - gpt-4.1 - gpt-4.1-mini - gpt-4.1-nano - gpt-5 - gpt-5-nano - gpt-5-mini - gpt-5.4-mini - gpt-5.4-nano - gpt-5-chat-latest - gpt-5.1 - gpt-5.2 - gpt-5.4 - gpt-5.5 - text-embedding-ada-002 - luminous-extended-control - luminous-embedding-128 - Pharia-1-Embedding-4608 - gemini-embedding-001 - claude-3-opus-20240229 - claude-sonnet-4-6 - custom-model - custom-embedding-model - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-3.1-pro-preview - gemini-3-flash-preview - gemini-3.1-flash-lite-preview - mistral-large-2411 - mistral-small-2503 - pixtral-large-2411 - pixtral-12b-2409 modelGroup: type: string enum: - chat - completion - embedding apiType: type: string enum: - chatCompletion - responses description: >- The API type for chat models. Defaults to chatCompletion when not specified. The responses API is only supported for OpenAI, Azure OpenAI, and OpenAI Compatible providers. isCustomModel: type: boolean example: true provider: type: string enum: - azureOpenAI - openAI - anthropic - googleVertexAI - googleGemini - googleGenAI - alephAlpha - awsBedrock - mistral connectionId: type: string format: uuid minLength: 36 maxLength: 36 description: >- The identifier for the large language model connection. openAI: type: object description: Metadata for OpenAI large language models. properties: customModel: type: string example: gpt-4-32k-0613 description: The custom model name. anthropic: type: object description: Metadata for Anthropic large language models. properties: customModel: type: string example: claude-opus-4-0 description: The custom model name. azureOpenAI: type: object description: Metadata for Azure OpenAI large language models. properties: resourceName: type: string description: >- The Azure OpenAI resource name. For more information, read the [Microsoft Azure OpenAI resource](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/create-resource?pivots=web-portal#create-a-resource) documentation. deploymentName: type: string description: >- The model deployment name. For more information, read the [Microsoft Azure OpenAI resource](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/create-resource?pivots=web-portal#deploy-a-model) documentation. apiVersion: type: string description: >- The API version in `YYYY-MM-DD` format (for example, `YYYY-MM-DD-preview`). For more information, read the [Microsoft Azure OpenAI REST API versioning](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/reference#rest-api-versioning) documentation. baseCustomUrl: type: string description: >- The custom URL to route connections between your clusters and Microsoft Azure OpenAI through a dedicated proxy for enhanced security. When set, `resourceName`, `deploymentName`, and `apiVersion` are ignored. For API key connections on 2025.20 and earlier use `https://.openai.azure.com/openai/deployments//?api-version=`. example: - >- https://.openai.azure.com/openai/deployments//chat/completions?api-version= - >- https://.openai.azure.com/openai/deployments//completions?api-version= - >- https://.openai.azure.com/openai/deployments//embeddings?api-version= googleVertexAI: type: object description: >- Metadata for Google Vertex AI large language models. properties: location: type: string apiEndpoint: type: string publisher: type: string googleGemini: type: object description: >- Metadata for Google Gemini large language models. properties: location: type: string googleGenAI: type: object description: Google GenAI specific meta data properties: location: type: string alephAlpha: type: object description: Metadata for Aleph Alpha large language models. properties: customModel: type: string example: luminous-003 description: The custom model name. baseCustomUrl: type: string example: https://api.aleph-alpha.com openAICompatible: type: object description: >- Metadata for OpenAI-compatible large language models. properties: customModel: type: string example: luminous-003 description: The custom model name. baseCustomUrl: type: string example: >- https://own-llm-deployment.company.com/openai/v1 customAuthHeader: type: string example: Ocp-Apim-Subscription-Key description: >- The API key will be sent via this http header if specified. resourceLevel: type: string enum: - organisation description: Scope for globally scoped resources. assignedToProjects: type: array items: type: string description: MongoDB ObjectId representing a project example: - 68edf5dd4c931f68d31111 - 690b02fc100e454245adde111 - 68e6eda61ff68d2111 referenceId: type: string description: The reference ID of the large language model. format: uuid _id: type: string pattern: ^[a-z0-9]{24}$ minLength: 24 maxLength: 24 createdAt: type: integer description: Unix-timestamp example: 1694518620 minimum: 0 maximum: 2147483647 lastChanged: type: integer description: Unix-timestamp example: 1694518620 minimum: 0 maximum: 2147483647 createdBy: type: string pattern: ^[a-z0-9]{24}$ minLength: 24 maxLength: 24 lastChangedBy: type: string pattern: ^[a-z0-9]{24}$ minLength: 24 maxLength: 24 description: > The IEntityMeta defines meta information every entity within the system has. These are dates when a resource was created and modified as well as information about the user who initially created a resource and who modified it the last time. total: type: integer example: 1 nextCursor: nullable: true type: string pattern: ^[a-z0-9]{24}$ minLength: 24 maxLength: 24 previousCursor: nullable: true type: string pattern: ^[a-z0-9]{24}$ minLength: 24 maxLength: 24 '400': description: >- The server cannot or will not process the request due to something that is perceived to be a client error (e.g., malformed request syntax, invalid request message framing, or deceptive request routing) content: application/json: schema: type: object properties: type: type: string example: Bad Request title: type: string example: Bad Request Error status: type: number example: 400 detail: type: string example: Validation failed. Missing payload. instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 1000 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} '401': description: >- The request has not been applied because it lacks valid authentication credentials for the target resource. content: application/json: schema: type: object properties: type: type: string example: Unauthorized title: type: string example: Unauthorized Error status: type: number example: 401 detail: type: string instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 401 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} '402': description: Upgrade your Plan to increase your Quota. content: application/json: schema: type: object properties: type: type: string example: Payment Required title: type: string example: Payment Required Error status: type: number example: 402 detail: type: string example: Validation failed. Missing payload. instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 402 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} '403': description: The server understood the request but refuses to authorize it. content: application/json: schema: type: object properties: type: type: string example: Forbidden title: type: string example: Forbidden Error status: type: number example: 403 detail: type: string instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 1000 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} '404': description: >- The origin server did not find a current representation for the target resource or is not willing to disclose that one exists. content: application/json: schema: type: object properties: type: type: string example: Not Found title: type: string example: Not Found Error status: type: number example: 404 detail: type: string instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 1000 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} logLevel: type: string example: error '405': description: >- The method received in the request-line is known by the origin server but not supported by the target resource. content: application/json: schema: type: object properties: type: type: string example: Method Not Allowed title: type: string example: Method Not Allowed Error status: type: number example: 405 detail: type: string instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 1000 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} '409': description: The request conflicts with current state of the server. content: application/json: schema: type: object properties: type: type: string example: Conflict title: type: string example: Conflict Error status: type: number example: 409 detail: type: string instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 1004 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} '413': description: The request entity is larger than limits defined by server. content: application/json: schema: type: object properties: type: type: string example: Payload Too Large title: type: string example: Payload Too Large Error status: type: number example: 413 detail: type: string instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 1000 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} '500': description: >- The server encountered an unexpected condition that prevented it from fulfilling the request. content: application/json: schema: type: object properties: type: type: string example: Internal Server Error title: type: string example: Internal Server Error status: type: number example: 500 detail: type: string instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 1000 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} '501': description: >- The server does not support the functionality required to fulfill the request. content: application/json: schema: type: object properties: type: type: string example: Not Implemented title: type: string example: Not Implemented Error status: type: number example: 501 detail: type: string instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 1009 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} '502': description: >- The server, while acting as a gateway or proxy, received an invalid response from an inbound server it accessed while attempting to fulfill the request. content: application/json: schema: type: object properties: type: type: string example: Bad Gateway title: type: string example: Bad Gateway Error status: type: number example: 502 detail: type: string instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 1000 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} '503': description: The server is not ready to handle the request. content: application/json: schema: type: object properties: type: type: string example: Service Unavailable title: type: string example: Service Unavailable Error status: type: number example: 503 detail: type: string instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 503 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} '504': description: >- The server, while acting as a gateway or proxy, did not receive a timely response from an upstream server it needed to access in order to complete the request. content: application/json: schema: type: object properties: type: type: string example: Gateway Timeout title: type: string example: Gateway Timeout Error status: type: number example: 504 detail: type: string instance: type: string example: /v2.0/flows/5ce7c2d833ea1e04d7e6c432 code: type: string example: 1000 traceId: type: string example: api--f84324f4-98eb-4f02-abdd-375a2e6c3c1f details: type: object example: {} security: - APIKeyHeader: [] - APIKeyQueryParam: [] - CXoneTokenHeader: [] - OAuth2: [] components: securitySchemes: APIKeyHeader: type: apiKey in: header name: X-API-Key description: Supply the API Key in the HTTP-Header APIKeyQueryParam: type: apiKey in: query name: api_key description: Supply the API Key in the Url-Query CXoneTokenHeader: type: apiKey in: header name: x-cxone-authorization description: >- Supply the CXone Token in the HTTP-Header containing the word "Bearer" followed by a space and a Token String. Applicable only in CXone integrated environments. OAuth2: type: oauth2 flows: password: tokenUrl: /auth/oauth2/token refreshUrl: /auth/oauth2/token scopes: {} authorizationCode: authorizationUrl: /auth/oauth2/authorize tokenUrl: /auth/oauth2/token scopes: {} BasicAuth: type: http scheme: basic description: Basic Authentication used by routes designed for the Management-UI. ````