> ## Documentation Index > Fetch the complete documentation index at: https://docs.fiddler.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create new LLM provider > Create a new LLM provider with credentials and models ## OpenAPI ````yaml POST /v3/llm-gateway/providers openapi: 3.0.3 info: title: Fiddler API - 2.0 description: APIs to interact with Fiddler termsOfService: https://fiddler.ai/about/terms contact: email: support@fiddler.ai license: name: Proprietary url: '2.0' version: '2.0' servers: [] security: - BearerAuth: [] tags: - name: access-key description: CRUD operations for API keys - name: span-v3 - name: aggregation-invalidation-request-v3 description: Endpoints related to retrieving aggregation invalidation requests - name: alert-rules-v3 description: CRUD for Alert Rules, Summary, and Stats APIs - name: application-v3 - name: auth description: Authentication strategies and login flows - name: baseline-v3 description: CRUD for baseline - name: catalog-v3 description: >- Entity catalog provides paginated, searchable discovery of entity names (attribute keys, agent names, span types, span names, score names, evaluator config names) and their distinct values. Powered by ClickHouse materialized views — no worker or PostgreSQL dependency. - name: chart-annotation-v3 description: Endpoints related to retrieving chart annotations - name: chart-v3 description: CRUD for chart - name: queries-v3 description: v3 queries API - name: configuration-v3 description: CRUD for configurations - name: cost-evaluators-v3 description: > Paginated roll-up of per-evaluator LLM cost and token usage, aggregated hourly. Available only on deployments with evaluator cost reporting enabled. - name: custom-metrics-v3 - name: dimensionality-reduction-v3 - name: environment-v3 description: Endpoints related to environment management - name: evals - name: datasets - name: evaluation-v3 - name: evaluator-v3 - name: rule-evaluators-v3 - name: experiment-v3 - name: explainability-v3 - name: llm_rca-v3 - name: file-upload description: Endpoints related to file uploading. - name: fql-expressions-v3 description: > Endpoints for listing FQL (Fiddler Query Language) functions available for GenAI custom metrics. Used by the frontend for autocomplete and signature hints in the FQL editor. - name: genai-alert-rules-v3 description: CRUD API for GenAI Alert Rules - name: genai-custom-metrics-v3 description: API for GenAI Custom Metrics - name: genai-metrics-v3 description: >- Endpoints for pre-aggregated GenAI metrics. All metric data is pre-aggregated hourly by a Celery-based metric collector; no real-time aggregation is performed at request time. - name: guardrails-api description: Endpoints related to retrieving Guardrails specific data - name: ingestion-v3 - name: intercom-api description: Endpoints related to intercom APIs - name: jobs-v3 - name: llm-gateway-v3 - name: auth-login - name: auth-logout - name: mcp-client-setup-v3 description: Endpoints for retrieving MCP client setup instructions. - name: metrics-v3 description: Metrics endpoints - name: model-v3 - name: dashboard-v3 - name: model-deployment-v3 - name: monitoring-summary-v3 - name: histograms-v3 - name: organization-roles-v3 description: Update user org role - name: organization-settings-v3 description: Update organization settings such as timezone, email configuration, etc. - name: pagerduty-api description: CRUD for Pagerduty services. - name: project-v3 - name: project-roles-v3 description: Project role assignment management - name: scores-v3 description: Unified CRUD for scores and annotations - name: searchable-text-key-v3 description: >- Manage the global searchable text keys table that controls which OTel attribute keys are routed to the full-text-searchable `ValueContent` column in the unified attributes table. Changes propagate to the backing ClickHouse dictionary within 1-2 minutes and affect all tenants. - name: segments-v3 - name: semantic-mapping-v3 description: >- Manage the global semantic name mappings table that maps raw OTel attribute keys to canonical semantic concepts. Changes propagate to the backing ClickHouse dictionary within 1-2 minutes and affect all tenants. - name: server-info-v3 description: Endpoints related to retrieving server information - name: service-account description: > Service accounts and their API keys. A human Org Admin manages the service accounts of their own organization: create, read, update, and enable/disable (there is no delete — an account is disabled instead), and issue, rename, re-date, enable/disable, and revoke each account's API keys. An API key is an `fks_` secret that inherits the account's grants and cannot manage service accounts; an active, unexpired key must be disabled before it can be revoked, and it authenticates only while both it and its account are active. Scopes here are capability scopes (what the account may do), not OAuth scopes. - name: sessions-v3 description: v3 session APIs - name: team-roles-v3 - name: team-v3 - name: traces-v3 description: v3 trace api for monitoring - name: fetch-sessions-v3 description: v3 fetch sessions api for monitoring - name: user-access-key description: > CRUD operations for user API keys. All endpoints are user-scoped — each user can only operate on their own API keys. No one including Org admins have access to other users' API keys. - name: users-v3 - name: version-compatibility-v3 - name: webhooks externalDocs: url: https://docs.fiddler.ai description: Find out more about Fiddler paths: /v3/llm-gateway/providers: post: tags: - llm-gateway-v3 summary: Create new LLM provider description: Create a new LLM provider with credentials and models operationId: createLLMProviderV3 requestBody: content: application/json: schema: $ref: '#/components/schemas/LLMProviderRequest' examples: openai_provider: summary: Create OpenAI provider with API key value: provider: OpenAI credentials: - name: Production Key credential_config: credential_type: api_key api_key: sk-... models: - name: gpt-4 - name: gpt-3.5-turbo anthropic_provider: summary: Create Anthropic provider with AWS role value: provider: Anthropic credentials: - name: AWS Bedrock Access credential_config: credential_type: iam cross_account_role_arn: arn:aws:iam::CUSTOMER-ACCOUNT:role/BedrockAccessRole external_id: unique-external-id-for-customer-123 region: us-east-1 models: - name: sonnet-3.7 - name: haiku-3 vertex_ai_provider: summary: Create Vertex AI provider with GCP service account value: provider: vertex_ai credentials: - name: GCP Service Account credential_config: credential_type: gcp_service_account service_account_json: '{"type":"service_account","project_id":"my-project"}' vertex_project: my-project-123 vertex_location: us-central1 models: - name: gemini-2.5-pro - name: gemini-2.5-flash databricks_provider: summary: Create Databricks provider with PAT and workspace URL value: provider: Databricks api_base: https://adb-xxx.azuredatabricks.net/serving-endpoints credentials: - name: Databricks PAT credential_config: credential_type: api_key api_key: dapi... models: - name: databricks-meta-llama-3-1-405b-instruct - name: my-custom-serving-endpoint databricks_oauth2_provider: summary: Create Databricks provider with OAuth2 client credentials value: provider: Databricks api_base: https://adb-xxx.azuredatabricks.net/serving-endpoints credentials: - name: Databricks Service Principal credential_config: credential_type: oauth2_client_credentials token_url: https://adb-xxx.azuredatabricks.net/oidc/v1/token client_id: 00000000-0000-0000-0000-000000000000 client_secret: dose... scope: all-apis models: - name: databricks-meta-llama-3-1-405b-instruct - name: my-custom-serving-endpoint responses: '200': description: LLM provider created successfully content: application/json: schema: allOf: - $ref: '#/components/schemas/ApiResponse' - type: object properties: data: $ref: '#/components/schemas/LLMProvider' examples: success: summary: Provider created successfully value: api: v3 data: id: 2 uuid: 550e8400-e29b-41d4-a716-446655440003 provider: OpenAI credentials: - name: Production Key uuid: 550e8400-e29b-41d4-a716-446655440004 credential_type: api_key models: - name: gpt-4 uuid: 550e8400-e29b-41d4-a716-446655440008 state: active - name: gpt-3.5-turbo uuid: 550e8400-e29b-41d4-a716-446655440009 state: deprecating retire_at: '2026-12-11' created_at: '2025-01-08T12:00:00Z' updated_at: '2025-01-08T12:00:00Z' created_by: id: 550e8400-e29b-41d4-a716-446655440002 full_name: Joe Schmoe email: joe_schmoe@email.com success_oauth2: summary: Provider created successfully with OAuth2 client credentials value: api: v3 data: id: 3 uuid: 550e8400-e29b-41d4-a716-446655440020 provider: Databricks api_base: https://adb-xxx.azuredatabricks.net/serving-endpoints credentials: - name: Databricks Service Principal uuid: 550e8400-e29b-41d4-a716-446655440021 credential_type: oauth2_client_credentials models: - name: databricks-meta-llama-3-1-405b-instruct uuid: 550e8400-e29b-41d4-a716-446655440022 state: active created_at: '2025-01-08T12:00:00Z' updated_at: '2025-01-08T12:00:00Z' created_by: id: 550e8400-e29b-41d4-a716-446655440002 full_name: Joe Schmoe email: joe_schmoe@email.com '400': $ref: '#/components/responses/400' '401': $ref: '#/components/responses/401' '500': $ref: '#/components/responses/500' components: schemas: LLMProviderRequest: type: object title: LLM Provider Request description: Request body for creating an LLM provider required: - provider - credentials - models properties: provider: description: Name of the LLM provider type: string example: OpenAI api_base: description: >- Custom API base URL. Required for some providers (e.g., Databricks), optional for others (e.g., Bedrock VPC endpoints). Must use HTTPS. type: string maxLength: 512 nullable: true example: https://adb-xxx.azuredatabricks.net/serving-endpoints credentials: description: List of credentials for the provider type: array items: $ref: '#/components/schemas/CredentialRequest' models: description: List of models supported by this provider type: array items: $ref: '#/components/schemas/ModelCompactRequest' ApiResponse: type: object description: | Response object for standard API responses. properties: api_version: type: string default: '3.0' enum: - '2.0' - '3.0' description: | API version. kind: type: string default: NORMAL enum: - NORMAL description: | Type of response, indicating a normal response. LLMProvider: type: object description: Details of an LLM provider required: - id - uuid - provider - credentials - models - created_by - created_at - updated_at allOf: - type: object properties: id: description: Unique identifier of the provider type: integer example: 1 uuid: description: UUID of the provider type: string format: uuid example: 550e8400-e29b-41d4-a716-446655440000 provider: description: Name of the provider type: string example: OpenAI api_base: description: >- Custom API base URL for providers with customer-specific endpoints type: string maxLength: 512 nullable: true credentials: description: List of credentials for this provider type: array items: $ref: '#/components/schemas/CredentialCompactResponse' models: description: >- Models this organization has saved for the provider, each carrying its catalog lifecycle type: array items: $ref: '#/components/schemas/SavedModelResponse' created_by: $ref: '#/components/schemas/UserCompact' - $ref: '#/components/schemas/CreateUpdateTimestamp' CredentialRequest: type: object title: Credential Request description: Request body for creating a credential required: - name - credential_config properties: name: description: Human-readable name for the credential type: string example: Production Key credential_config: oneOf: - $ref: '#/components/schemas/APIKeyConfig' - $ref: '#/components/schemas/IAMConfig' - $ref: '#/components/schemas/GCPServiceAccountConfig' - $ref: '#/components/schemas/EntraIDConfig' - $ref: '#/components/schemas/AWSAccessKeyConfig' - $ref: '#/components/schemas/OAuth2ClientCredentialsConfig' discriminator: propertyName: credential_type mapping: api_key: '#/components/schemas/APIKeyConfig' iam: '#/components/schemas/IAMConfig' gcp_service_account: '#/components/schemas/GCPServiceAccountConfig' entra_id: '#/components/schemas/EntraIDConfig' aws_access_key: '#/components/schemas/AWSAccessKeyConfig' oauth2_client_credentials: '#/components/schemas/OAuth2ClientCredentialsConfig' ModelCompactRequest: type: object title: Model Compact Request description: Request body for a model required: - name properties: name: description: Human-readable name for this model type: string maxLength: 128 uuid: description: UUID for existing model type: string format: uuid nullable: true CredentialCompactResponse: title: Credential Compact Response description: Compact credential representation that includes the credential type allOf: - $ref: '#/components/schemas/UUIDAndNameCompactResponse' - type: object properties: credential_type: description: >- Credential type (e.g., api_key, gcp_service_account, iam, entra_id, aws_access_key, oauth2_client_credentials) type: string enum: - api_key - iam - gcp_service_account - entra_id - aws_access_key - oauth2_client_credentials maxLength: 64 required: - credential_type SavedModelResponse: type: object title: Saved Model Response description: > A model the organization has saved, with its catalog lifecycle joined on. The lifecycle fields are not stored: they are read from the catalog on every request, so a model the vendor retires after it was saved starts reporting `retired` without a migration. allOf: - $ref: '#/components/schemas/UUIDAndNameCompactResponse' - type: object properties: state: description: >- Lifecycle state: 'active', 'deprecating' or 'retired'. Advisory -- a retired model is still returned, and still callable. type: string enum: - active - deprecating - retired retire_at: description: ISO date the provider stops serving the model type: string format: date nullable: true user_defined: description: Written in by the user rather than drawn from the catalog type: boolean required: - state UserCompact: type: object title: UserCompactV3 description: > Compact version of a user which can be included in the response of relevant APIs. required: - id - email properties: id: type: string format: uuid readOnly: true description: | Unique identifier for the user. full_name: type: string readOnly: true description: | Full name of the user. email: type: string format: email description: | Email address of the user. CreateUpdateTimestamp: type: object required: - created_at - updated_at properties: created_at: type: string format: date-time readOnly: true description: | Date and time when the object was created. updated_at: type: string format: date-time readOnly: true description: | Date and time when the object was last updated. ErrorResponse: type: object description: | Response object for errors returned by the API. properties: api_version: type: string default: '3.0' enum: - '2.0' - '3.0' description: | API version of the response. kind: type: string default: ERROR enum: - ERROR description: | Type of response, usually indicating an error. error: type: object properties: code: type: integer format: int32 description: > Represents the code for this error, typically an HTTP response code. default: 400 enum: - 400 - 401 - 403 - 404 - 409 - 410 - 422 - 429 - 500 - 501 - 503 message: type: string description: > A human-readable message providing more details about the error. If there are multiple errors, it will be the message for the first error. example: Resource Not Found errors: type: array description: > Container for additional information regarding the error, especially for multiple errors. items: type: object properties: reason: type: string description: > Unique identifier for this error, different from the error code. example: ResourceNotFoundException message: type: string description: > A human-readable message providing more details about the error. If there is only one error, this field will match error.message. example: Resource Not Found help: type: string description: > Link to support or documentation providing more information on the error. APIKeyConfig: type: object title: API Key Configuration description: Configuration for API key-based authentication required: - credential_type - api_key properties: credential_type: description: Type of credential configuration type: string enum: - api_key example: api_key api_key: description: API key for the provider type: string format: password writeOnly: true maxLength: 4096 example: sk-... IAMConfig: type: object title: IAM Configuration description: Configuration for AWS cross-account role-based authentication required: - credential_type - cross_account_role_arn - external_id - region properties: credential_type: description: Type of credential configuration type: string enum: - iam example: iam cross_account_role_arn: description: ARN of the cross-account role type: string example: arn:aws:iam::CUSTOMER-ACCOUNT:role/BedrockAccessRole external_id: description: Unique external ID for the customer type: string format: password writeOnly: true example: unique-external-id-for-customer-123 region: description: AWS region for the service type: string example: us-east-1 GCPServiceAccountConfig: type: object title: GCP Service Account Configuration description: Configuration for GCP service account authentication (Vertex AI) required: - credential_type - service_account_json - vertex_project - vertex_location properties: credential_type: description: Type of credential configuration type: string enum: - gcp_service_account example: gcp_service_account service_account_json: description: GCP service account key JSON (used for authentication) type: string format: password writeOnly: true maxLength: 65536 example: '{"type":"service_account","project_id":"my-project"}' vertex_project: description: Target GCP project for Vertex AI requests (e.g., my-project-123) type: string maxLength: 256 example: my-project-123 vertex_location: description: >- Target Vertex AI region for requests (e.g., us-central1, europe-west1) type: string maxLength: 64 example: us-central1 EntraIDConfig: type: object title: Microsoft Entra ID Configuration description: >- Configuration for Microsoft Entra ID client credentials authentication (Azure OpenAI / Azure AI) required: - credential_type - tenant_id - client_id - client_secret properties: credential_type: description: Type of credential configuration type: string enum: - entra_id example: entra_id tenant_id: description: Microsoft Entra ID tenant ID (directory ID) type: string maxLength: 256 example: 00000000-0000-0000-0000-000000000000 client_id: description: Microsoft Entra ID application (client) ID type: string maxLength: 256 example: 00000000-0000-0000-0000-000000000000 client_secret: description: Microsoft Entra ID client secret value type: string format: password writeOnly: true maxLength: 512 AWSAccessKeyConfig: type: object title: AWS Access Key Configuration description: Configuration for static AWS access key authentication (Bedrock) required: - credential_type - aws_access_key_id - aws_secret_access_key - region properties: credential_type: description: Type of credential configuration type: string enum: - aws_access_key example: aws_access_key aws_access_key_id: description: AWS access key ID type: string maxLength: 256 example: AKIAIOSFODNN7EXAMPLE aws_secret_access_key: description: AWS secret access key type: string format: password writeOnly: true maxLength: 256 region: description: AWS region (e.g., us-east-1) type: string maxLength: 32 example: us-east-1 OAuth2ClientCredentialsConfig: type: object title: OAuth2 Client Credentials Configuration description: >- Generic, provider-agnostic OAuth2 client-credentials (M2M) configuration. The gateway exchanges client_id/client_secret for a short-lived bearer token at token_url and sends it as an Authorization Bearer header. Works for any standard OAuth2 client-credentials provider (Databricks, etc. for now) — only the field values differ per provider, not the schema. The example values below are for a Databricks service principal (token_url = {workspace-host}/oidc/v1/token, scope = all-apis). required: - credential_type - token_url - client_id - client_secret - scope properties: credential_type: description: Type of credential configuration type: string enum: - oauth2_client_credentials example: oauth2_client_credentials token_url: description: >- OAuth2 token endpoint (e.g., Databricks {workspace-host}/oidc/v1/token). Must use HTTPS. type: string maxLength: 512 example: https://adb-xxx.azuredatabricks.net/oidc/v1/token client_id: description: OAuth2 client ID (service principal application ID) type: string maxLength: 256 example: 00000000-0000-0000-0000-000000000000 client_secret: description: OAuth2 client secret value type: string format: password writeOnly: true maxLength: 512 scope: description: OAuth2 scope to request (e.g., Databricks 'all-apis') type: string maxLength: 512 example: all-apis UUIDAndNameCompactResponse: type: object title: UUID and Name Compact Response description: Compact representation of an entity with UUID and name required: - uuid - name properties: uuid: description: Unique identifier for this entity type: string format: uuid name: description: Human-readable name for this entity type: string maxLength: 128 responses: '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' securitySchemes: BearerAuth: type: http scheme: bearer ````