Modules
API calls for all endpoints tagged AccessProfiles.
API calls for all endpoints tagged AnthropicIntegration.
API calls for all endpoints tagged AsyncJobs.
API calls for all endpoints tagged Audio.
API calls for all endpoints tagged AuditLogs.
API calls for all endpoints tagged AzureIntegration.
API calls for all endpoints tagged Batch.
API calls for all endpoints tagged BedrockIntegration.
API calls for all endpoints tagged Cache.
API calls for all endpoints tagged ChatCompletions.
API calls for all endpoints tagged CircuitBreaker.
API calls for all endpoints tagged CohereIntegration.
API calls for all endpoints tagged Compaction.
API calls for all endpoints tagged Configuration.
API calls for all endpoints tagged Containers.
API calls for all endpoints tagged CountTokens.
API calls for all endpoints tagged CursorIntegration.
API calls for all endpoints tagged Embeddings.
API calls for all endpoints tagged Files.
API calls for all endpoints tagged GenAIIntegration.
API calls for all endpoints tagged Governance.
API calls for all endpoints tagged Health.
API calls for all endpoints tagged Images.
API calls for all endpoints tagged Infrastructure.
API calls for all endpoints tagged LangChainIntegration.
API calls for all endpoints tagged LiteLLMIntegration.
API calls for all endpoints tagged Logging.
API calls for all endpoints tagged MCP.
API calls for all endpoints tagged MCPToolGroups.
API calls for all endpoints tagged Models.
API calls for all endpoints tagged OAuth.
API calls for all endpoints tagged OCR.
API calls for all endpoints tagged OpenAIIntegration.
API calls for all endpoints tagged Plugins.
API calls for all endpoints tagged PromptRepository.
API calls for all endpoints tagged Providers.
API calls for all endpoints tagged PydanticAIIntegration.
API calls for all endpoints tagged RBAC.
API calls for all endpoints tagged Realtime.
API calls for all endpoints tagged Rerank.
API calls for all endpoints tagged Responses.
API calls for all endpoints tagged Session.
API calls for all endpoints tagged Skills.
API calls for all endpoints tagged Teams.
API calls for all endpoints tagged TextCompletions.
API calls for all endpoints tagged Users.
API calls for all endpoints tagged Vault.
API calls for all endpoints tagged Videos.
API calls for all endpoints tagged Webhooks.
OTP application for ExBifrost.
Handle Tesla connections for ExBifrost.
Helper functions for deserializing responses into models
MCP client configuration for creating a new client (tool_pricing not available at creation). The schema varies based on connection_type: - HTTP/SSE: connection_string is required - STDIO: stdio_config is required - InProcess: server instance must be provided programmatically (Go package only)
AddMcpClientRequestOneOf model.
AddMcpClientRequestOneOf1 model.
AddMcpClientRequestOneOf2 model.
STDIO configuration (required for STDIO connection type)
TLS configuration for HTTP and SSE connections. Not applicable to stdio or inprocess connection types.
Add provider request. Keys are managed separately via /api/providers/{provider}/keys.
AddTeamMemberRequest model.
AddUserAccessProfileVirtualKey200Response model.
AddUserAccessProfileVirtualKey200ResponseVirtualKey model.
AddUserAccessProfileVirtualKeyRequest model.
AllSkillsVersionResponse model.
AnthropicContentBlock model.
For document content
For image/document content
AnthropicCountTokens200Response model.
AnthropicCreateBatchRequest model.
AnthropicCreateBatchRequestRequestsInner model.
AnthropicCreateComplete200Response model.
AnthropicCreateComplete200ResponseUsage model.
AnthropicCreateMessage200Response model.
AnthropicCreateMessage200ResponseDelta model.
AnthropicCreateMessage200ResponseError model.
AnthropicCreateMessage200ResponseUsage model.
AnthropicCreateMessage200ResponseUsageCacheCreation model.
AnthropicCreateMessage400Response model.
AnthropicDeleteFile200Response model.
AnthropicListBatches200Response model.
AnthropicListBatches200ResponseDataInner model.
AnthropicListBatches200ResponseDataInnerRequestCounts model.
AnthropicListFiles200Response model.
AnthropicListFiles200ResponseDataInner model.
AnthropicListModelsResponse model.
AnthropicListModelsResponseDataInner model.
AnthropicMessage model.
AnthropicMessageRequest model.
AnthropicMessageRequestMcpServersInner model.
AnthropicMessageRequestMcpServersInnerToolConfiguration model.
AnthropicMessageRequestMetadata model.
System prompt
AnthropicMessageRequestThinking model.
AnthropicMessageRequestToolChoice model.
AnthropicMessageRequestToolsInner model.
AnthropicMessageRequestToolsInnerUserLocation model.
AnthropicMessageResponse model.
AnthropicTextRequest model.
Request to assign a team to a business unit
AssignUserRoleRequest model.
Response returned when creating or polling an async job
The status of an async job
AttachRolesToAccessProfile200Response model.
AttachRolesToAccessProfileRequest model.
The CADF action performed.
Additional CADF data attached to an event.
A CADF-compliant audit event.
Classifies the audit event.
Distinct values available for each audit log filter dimension.
An id/name pair used for initiator and target filter dropdowns.
Response wrapper for a single audit log entry.
A paginated result of audit logs.
The CADF outcome of the action.
The CADF reason for an outcome (especially for failures).
A CADF resource (initiator, target, or observer).
The type of resource involved in an audit event (initiator or target).
The result of an audit log signature verification.
BatchCreateRequest model.
BatchCreateRequestRequestsInner model.
BatchCreateResponse model.
BatchListResponse model.
BatchRetrieveResponse model.
BatchRetrieveResponseErrors model.
BatchRetrieveResponseErrorsDataInner model.
BedrockBatchJobRequest model.
BedrockBatchJobRequestInputDataConfig model.
BedrockBatchJobRequestInputDataConfigS3InputDataConfig model.
BedrockBatchJobRequestOutputDataConfig model.
BedrockBatchJobRequestTagsInner model.
BedrockBatchJobResponse model.
BedrockBatchJobResponseVpcConfig model.
BedrockCancelBatchJob200Response model.
BedrockContentBlock model.
BedrockContentBlockDocument model.
BedrockContentBlockDocumentSource model.
BedrockContentBlockImage model.
BedrockContentBlockImageSource model.
BedrockContentBlockReasoningContent model.
BedrockContentBlockToolResult model.
BedrockContentBlockToolUse model.
BedrockConverseRequest model.
BedrockConverseRequestGuardrailConfig model.
BedrockConverseRequestInferenceConfig model.
BedrockConverseRequestPerformanceConfig model.
BedrockConverseRequestPromptVariablesValue model.
BedrockConverseRequestServiceTier model.
BedrockConverseRequestSystemInner model.
BedrockConverseRequestSystemInnerCachePoint model.
BedrockConverseRequestSystemInnerGuardContent model.
BedrockConverseRequestSystemInnerGuardContentText model.
BedrockConverseRequestToolConfig model.
BedrockConverseRequestToolConfigToolChoice model.
BedrockConverseRequestToolConfigToolChoiceTool model.
BedrockConverseRequestToolConfigToolsInner model.
BedrockConverseRequestToolConfigToolsInnerToolSpec model.
BedrockConverseRequestToolConfigToolsInnerToolSpecInputSchema model.
BedrockConverseResponse model.
BedrockConverseResponseOutput model.
Flat structure for streaming events matching actual Bedrock API response
BedrockConverseStream200ResponseDelta model.
BedrockConverseStream200ResponseDeltaReasoningContent model.
BedrockConverseStream200ResponseDeltaToolUse model.
BedrockConverseStream200ResponseMetrics model.
BedrockConverseStream200ResponseStart model.
BedrockConverseStream200ResponseStartToolUse model.
BedrockConverseStream200ResponseUsage model.
BedrockCountTokens200Response model.
BedrockCountTokensRequest model.
BedrockCountTokensRequestInput model.
BedrockError model.
Raw model invocation request. The body format depends on the model provider. For Anthropic models, use Anthropic format. For other models, use their native format.
BedrockListBatchJobs200Response model.
BedrockListBatchJobs200ResponseInvocationJobSummariesInner model.
BedrockMessage model.
BifrostCacheDebug model.
Cost breakdown for the request
Error response from Bifrost
BifrostErrorExtraFields model.
Token usage information
Additional fields included in responses
Budget configuration
BumpAllSkillsVersionRequest model.
Cache control settings for content blocks
CancelBatch200Response model.
CancelBatch200ResponseRequestCounts model.
ChatCompletionRequest model.
Predicted output content for the model to reference (OpenAI only). Can reduce latency.
Predicted content (string or array of content parts)
ChatCompletionRequestReasoning model.
Up to 4 sequences where the API will stop generating tokens
ChatCompletionRequestStreamOptions model.
ChatCompletionRequestToolChoice model.
ChatCompletionRequestToolChoiceOneOf model.
ChatCompletionRequestToolChoiceOneOfAllowedTools model.
ChatCompletionRequestToolChoiceOneOfAllowedToolsToolsInner model.
ChatCompletionRequestToolsInner model.
ChatCompletionRequestToolsInnerCustom model.
ChatCompletionRequestToolsInnerCustomFormat model.
ChatCompletionRequestToolsInnerCustomFormatGrammar model.
ChatCompletionRequestToolsInnerFunction model.
ChatCompletionRequestToolsInnerFunctionParameters model.
Web search options for chat completions (OpenAI only)
ChatCompletionRequestWebSearchOptionsUserLocation model.
ChatCompletionRequestWebSearchOptionsUserLocationApproximate model.
ChatCompletionResponse model.
ChatCompletionTokensDetails model.
Chat format - uses ChatAssistantMessageToolCall schema
ChatMessage model.
ChatMessageAnnotationsInner model.
ChatMessageAnnotationsInnerUrlCitation model.
Message content - can be a string or array of content blocks
ChatMessageContentOneOfInner model.
ChatMessageContentOneOfInnerFile model.
ChatMessageContentOneOfInnerImageUrl model.
ChatMessageContentOneOfInnerInputAudio model.
ChatPromptTokensDetails model.
Claude Code marketplace document generated by Bifrost.
Clear cache response
CloneAccessProfileRequest model.
Codex marketplace document generated by Bifrost.
CohereChatRequest model.
CohereChatRequestResponseFormat model.
CohereChatRequestThinking model.
CohereChatRequestToolsInner model.
CohereChatRequestToolsInnerFunction model.
CohereChatResponse model.
CohereChatResponseLogprobsInner model.
CohereChatResponseMessage model.
CohereChatResponseMessageContentInner model.
CohereChatResponseMessageContentInnerDocument model.
CohereChatResponseMessageContentInnerImageUrl model.
CohereChatV2200Response model.
CohereChatV2200ResponseDelta model.
CohereChatV2200ResponseDeltaMessage model.
Citations (for citation events)
CohereChatV2200ResponseDeltaMessageCitationsOneOf model.
CohereChatV2200ResponseDeltaMessageCitationsOneOfSourcesInner model.
Content for content events
CohereChatV2200ResponseDeltaMessageContentOneOf model.
Tool calls (for tool-call events)
CohereChatV2200ResponseDeltaMessageToolCallsOneOf model.
CohereChatV2200ResponseDeltaUsage model.
CohereChatV2200ResponseDeltaUsageBilledUnits model.
CohereCountTokensRequest model.
CohereCountTokensResponse model.
Metadata returned by the tokenize endpoint
API version metadata
CohereEmbeddingRequest model.
CohereEmbeddingRequestInputsInner model.
CohereEmbeddingResponse model.
Embedding data object with different types
Image information in the response
Metadata in embedding response
API version information
CohereError model.
CohereMessage model.
Message content - can be a string or array of content blocks
CohereRerank200Response model.
CohereRerank200ResponseResultsInner model.
CohereRerankRequest model.
CohereRerankRequestDocumentsInner model.
CohereRerankRequestDocumentsInnerOneOf model.
CommitPromptSessionRequest model.
Concurrency settings
CountTokensRequest model.
CountTokensResponse model.
CreateAccessProfile201Response model.
CreateAccessProfileRequest model.
Create budget request
Business unit governance operation response
Business unit configuration with governance association
Create business unit governance request. The business unit is identified by the {id} path parameter. At least one of budget or rate_limit is required.
Streaming chat completion response (SSE format)
CreateChatCompletion200ResponseChoicesInner model.
For streaming chat completions
CreateChatCompletion200ResponseChoicesInnerDeltaAudio model.
CreateChatCompletion200ResponseChoicesInnerDeltaReasoningDetailsInner model.
CreateChatCompletion200ResponseChoicesInnerDeltaToolCallsInner model.
CreateChatCompletion200ResponseChoicesInnerDeltaToolCallsInnerFunction model.
CreateChatCompletion200ResponseChoicesInnerLogProbs model.
CreateChatCompletion200ResponseChoicesInnerLogProbsContentInner model.
CreateChatCompletion200ResponseChoicesInnerLogProbsContentInnerTopLogprobsInner model.
CreateCompaction200Response model.
CreateCompaction200ResponseUsage model.
CreateCompaction200ResponseUsageInputTokensDetails model.
CreateCompaction200ResponseUsageOutputTokensDetails model.
CreateCompactionRequest model.
Conversation to compact. Required unless previous_response_id is provided. Can be a string or array of ResponsesMessage objects. Compaction items from prior responses (type "response.compaction") may be included in the array.
CreateContainer200Response model.
Response from creating a file in a container
Request to create a file in a container by referencing an existing file
CreateContainerRequest model.
Create customer request
CreateFolder200Response model.
CreateMcpToolGroup201Response model.
CreateMcpToolGroupRequest model.
Request to create a new model config
Plugin operation response
Create plugin request
Request body for creating a pricing override.
CreatePrompt200Response model.
CreatePromptRequest model.
CreatePromptSession200Response model.
CreatePromptSessionRequest model.
CreatePromptVersion200Response model.
CreatePromptVersionRequest model.
Create rate limit request
Streaming responses API response (SSE format)
CreateResponse200ResponseItem model.
CreateResponse200ResponseItemContent model.
CreateResponse200ResponseItemContentOneOfInner model.
CreateResponse200ResponseItemContentOneOfInnerAnnotationsInner model.
CreateResponse200ResponseItemContentOneOfInnerInputAudio model.
CreateResponse200ResponseItemSummaryInner model.
CreateRole200Response model.
CreateRoleRequest model.
Request to create a routing rule
CreateSkillRequest model.
CreateSpeech200Response model.
CreateSpeech200ResponseUsage model.
CreateTeam200Response model.
CreateTeamRequest model.
Streaming text completion response
CreateTranscription200Response model.
CreateTranscription200ResponseUsage model.
CreateTranscription200ResponseUsageInputTokenDetails model.
CreateUser200Response model.
CreateUserRequest model.
Create virtual key request
CreateVirtualKeyRequestMcpConfigsInner model.
CreateVirtualKeyRequestProviderConfigsInner model.
CursorBedrockCountTokensRequest model.
CursorBedrockCountTokensRequestInput model.
Customer configuration
Customer operation response
DeleteFile200Response model.
Delete logs request
Delete MCP logs request
DeleteMcpToolGroup200Response model.
DetachUserAccessProfile200Response model.
MCP client configuration for updating an existing client (includes tool_pricing)
Per-virtual-key tool access configuration for an MCP client
EmbeddingRequest model.
Input for embedding - text or token arrays
EmbeddingResponse model.
EmbeddingResponseDataInner model.
EmbeddingResponseDataInnerEmbedding model.
ErrorField model.
MCP tool execution response.
MCP tool execution request. The schema depends on the format query parameter: - format=chat or empty (default): Use ChatAssistantMessageToolCall schema - format=responses: Use ResponsesToolMessage schema
Fallback model configuration
FileListResponse model.
FileListResponseDataInner model.
FileUploadResponse model.
GeminiContent model.
GeminiCountTokens200Response model.
GeminiCountTokens200ResponsePromptTokensDetailsInner model.
GeminiCountTokensRequest model.
GeminiCreateCachedContentRequest model.
GeminiEmbeddingRequest model.
GeminiEmbeddingResponse model.
GeminiEmbeddingResponseEmbeddingsInner model.
GeminiEmbeddingResponseEmbeddingsInnerStatistics model.
GeminiEmbeddingResponseMetadata model.
GeminiError model.
GeminiErrorError model.
GeminiErrorErrorDetailsInner model.
GeminiGenerationRequest model.
GeminiGenerationRequestGenerationConfig model.
GeminiGenerationRequestGenerationConfigModelSelectionConfig model.
GeminiGenerationRequestGenerationConfigRoutingConfig model.
GeminiGenerationRequestGenerationConfigRoutingConfigAutoMode model.
GeminiGenerationRequestGenerationConfigRoutingConfigManualMode model.
GeminiGenerationRequestGenerationConfigSpeechConfig model.
GeminiGenerationRequestGenerationConfigSpeechConfigMultiSpeakerVoiceConfig model.
GeminiGenerationRequestGenerationConfigSpeechConfigMultiSpeakerVoiceConfigSpeakerVoiceConfigsInner model.
GeminiGenerationRequestGenerationConfigSpeechConfigVoiceConfig model.
GeminiGenerationRequestGenerationConfigSpeechConfigVoiceConfigPrebuiltVoiceConfig model.
GeminiGenerationRequestGenerationConfigThinkingConfig model.
GeminiGenerationRequestSafetySettingsInner model.
GeminiGenerationRequestToolConfig model.
GeminiGenerationRequestToolConfigFunctionCallingConfig model.
GeminiGenerationRequestToolConfigRetrievalConfig model.
GeminiGenerationRequestToolConfigRetrievalConfigLatLng model.
GeminiGenerationRequestToolsInner model.
GeminiGenerationRequestToolsInnerComputerUse model.
GeminiGenerationRequestToolsInnerEnterpriseWebSearch model.
GeminiGenerationRequestToolsInnerFunctionDeclarationsInner model.
GeminiGenerationRequestToolsInnerGoogleMaps model.
GeminiGenerationRequestToolsInnerGoogleSearch model.
GeminiGenerationRequestToolsInnerGoogleSearchRetrieval model.
GeminiGenerationRequestToolsInnerGoogleSearchRetrievalDynamicRetrievalConfig model.
GeminiGenerationRequestToolsInnerGoogleSearchTimeRangeFilter model.
GeminiGenerationRequestToolsInnerRetrieval model.
GeminiGenerationRequestToolsInnerRetrievalExternalApi model.
GeminiGenerationRequestToolsInnerRetrievalExternalApiAuthConfig model.
GeminiGenerationRequestToolsInnerRetrievalExternalApiAuthConfigApiKeyConfig model.
GeminiGenerationRequestToolsInnerRetrievalExternalApiAuthConfigGoogleServiceAccountConfig model.
GeminiGenerationRequestToolsInnerRetrievalExternalApiAuthConfigHttpBasicAuthConfig model.
GeminiGenerationRequestToolsInnerRetrievalExternalApiAuthConfigOauthConfig model.
GeminiGenerationRequestToolsInnerRetrievalExternalApiAuthConfigOidcConfig model.
GeminiGenerationRequestToolsInnerRetrievalExternalApiElasticSearchParams model.
GeminiGenerationRequestToolsInnerRetrievalVertexAiSearch model.
GeminiGenerationRequestToolsInnerRetrievalVertexAiSearchDataStoreSpecsInner model.
GeminiGenerationRequestToolsInnerRetrievalVertexRagStore model.
GeminiGenerationRequestToolsInnerRetrievalVertexRagStoreRagResourcesInner model.
GeminiGenerationRequestToolsInnerRetrievalVertexRagStoreRagRetrievalConfig model.
GeminiGenerationRequestToolsInnerRetrievalVertexRagStoreRagRetrievalConfigFilter model.
GeminiGenerationRequestToolsInnerRetrievalVertexRagStoreRagRetrievalConfigHybridSearch model.
GeminiGenerationRequestToolsInnerRetrievalVertexRagStoreRagRetrievalConfigRanking model.
GeminiGenerationResponse model.
GeminiGenerationResponseCandidatesInner model.
GeminiGenerationResponseCandidatesInnerLogprobsResult model.
GeminiGenerationResponseCandidatesInnerLogprobsResultChosenCandidatesInner model.
GeminiGenerationResponseCandidatesInnerLogprobsResultTopCandidatesInner model.
GeminiGenerationResponseCandidatesInnerSafetyRatingsInner model.
GeminiGenerationResponseCandidatesInnerUrlContextMetadata model.
GeminiGenerationResponseCandidatesInnerUrlContextMetadataUrlMetadataInner model.
GeminiGenerationResponsePromptFeedback model.
GeminiGenerationResponseUsageMetadata model.
GeminiListFiles200Response model.
GeminiListModelsResponse model.
GeminiListModelsResponseModelsInner model.
GeminiPart model.
GeminiPartCodeExecutionResult model.
GeminiPartExecutableCode model.
GeminiPartFileData model.
GeminiPartFunctionCall model.
GeminiPartFunctionResponse model.
GeminiPartInlineData model.
GeminiPartVideoMetadata model.
Schema object for defining input/output data types (OpenAPI 3.0 subset)
GeminiUpdateCachedContentRequest model.
GeminiUploadFile200Response model.
GeminiUploadFile200ResponseFile model.
GeminiUploadFile200ResponseFileError model.
GeminiUploadFile200ResponseFileVideoMetadata model.
JSON metadata part; see encoding at the path for contentType application/json.
GeminiUploadFileRequestMetadataFile model.
Returned by GET /api/access-profiles/{id}. Includes role attachments and the count of users holding a copy.
GetAccessProfile200ResponseRolesInner model.
GetAccessProfileVersion200Response model.
Available filter data response
GetBatchResults200Response model.
GetBatchResults200ResponseResultsInner model.
GetBatchResults200ResponseResultsInnerResponse model.
GetBatchResults200ResponseResultsInnerResult model.
Single business unit with governance and team count
GetCircuitBreakerState200Response model.
Runtime state of a single circuit (main circuit or per-key sub-circuit).
Full runtime configuration for complexity routing analysis.
Editable keyword lists used by the complexity analyzer. Only the four user-facing dimensions are exposed; reasoning_keywords entries drive the reasoning tier override. Matching is normalized to lowercase and duplicates are removed on save.
Score thresholds for complexity tier classification. All values must satisfy 0 < simple_medium < medium_complex < complex_reasoning < 1.
Configuration response
Authentication configuration
Client configuration
Compat plugin configuration
Header filter configuration
Public base URL Bifrost uses as the redirect_uri when acting as an OAuth client to upstream MCP servers (Notion, Jira, etc.). Set when Bifrost's callback endpoint is reached via a different URL than its server-side metadata. Supports env var syntax ("env.MY_VAR").
GetConfigResponseClientConfigMcpExternalClientUrlOneOf model.
OAuth2 authorization server settings for /mcp. Only relevant when mcp_server_auth_mode is 'both' or 'oauth'.
Framework configuration
Restart required configuration
GetCurrentUserPermissions200Response model.
GetCustomer200Response model.
Consolidated payload containing every metric shown on the workspace dashboard. Each section mirrors the response of its dedicated endpoint, so consumers can integrate a single call instead of orchestrating many.
Dimension values ranked by usage with trend comparison
GetDashboard200ResponseDimensionRankingsValueRankingsInner model.
Percentage change versus the previous comparable period
MCP usage tab metrics
Time-bucketed MCP cost histogram
Time-bucketed MCP cost data
Top MCP tools by call count (limit 10)
Aggregated stats for a single MCP tool
Parameters the dashboard data was computed with
Model Rankings tab data
Overview tab metrics
Provider Usage tab metrics
Dropped requests response
GetGovernanceTeam200Response model.
Paginated logs for a single parent-request session
Pagination metadata. Session logs are always sorted by timestamp; the sort_by field is not configurable.
Aggregate totals for a single parent-request session
Time-bucketed cost histogram with model breakdown
Time-bucketed cost data with model breakdown
Dimension-grouped cost histogram result
Time-bucketed cost data grouped by an arbitrary dimension
Dimension-grouped latency histogram result
Time-bucketed latency data grouped by an arbitrary dimension
Dimension-grouped token histogram result
Time-bucketed token usage grouped by an arbitrary dimension
Time-bucketed request count histogram
Time-bucketed request count
Time-bucketed latency histogram
Time-bucketed latency percentiles
Time-bucketed model usage histogram
Time-bucketed model usage with success/error breakdown
Usage statistics for a single model
Time-bucketed cost histogram with provider breakdown
Time-bucketed cost data with provider breakdown
Time-bucketed latency histogram with provider breakdown
Time-bucketed latency data with provider breakdown
Latency statistics for a single provider
Time-bucketed token histogram with provider breakdown
Time-bucketed token usage with provider breakdown
Token statistics for a single provider
Time-bucketed token usage histogram
Time-bucketed token usage
Paginated list of MCP clients.
MCP tool execution log entry
Search MCP logs response
MCP tool execution log entry
GetMcpLogs200ResponsePagination model.
Available MCP log filter data
MCP tool log statistics
GetModelConfig200Response model.
Models ranked by usage with trend comparison
GetModelRankings200ResponseRankingsInner model.
Percentage change versus the previous comparable period
Global proxy configuration
GetRolePermissions200Response model.
GetRolePermissions200ResponsePermissionsInner model.
GetRoutingRule200Response model.
GetTeamMembers200Response model.
GetTeamMembers200ResponseMembersInner model.
GetUserTeams200Response model.
GetUserTeams200ResponseTeamsInner model.
GetUserVirtualKeysByEmail200Response model.
GetUserVirtualKeysByEmail200ResponseVirtualKeysInner model.
GetVirtualKey200Response model.
GetVirtualKeyQuota401Response model.
Health check response
Streaming response chunk for image edit. Sent via Server-Sent Events (SSE) when stream=true.
ImageGeneration200Response model.
Streaming response chunk for image generation. Sent via Server-Sent Events (SSE). Providers may return either b64_json (base64-encoded image data) or url (public URL to the image).
ImageGeneration200ResponseDataInner model.
ImageGeneration200ResponseUsage model.
ImageGeneration200ResponseUsageInputTokensDetails model.
ImageGenerationRequest model.
Auth enabled status response
IssueWsTicket200Response model.
API key configuration
Azure-specific key configuration
AWS Bedrock-specific key configuration
KeyBedrockKeyConfigBatchS3Config model.
KeyBedrockKeyConfigBatchS3ConfigBucketsInner model.
Ollama-specific key configuration
Replicate-specific key configuration
API key value (redacted in responses)
Vertex-specific key configuration
VLLM-specific key configuration
ListAccessProfileAuditLogsById200Response model.
ListAccessProfileAuditLogsById200ResponseAuditLogsInner model.
ListAccessProfileVersions200Response model.
ListAccessProfileVersions200ResponseVersionsInner model.
ListAccessProfiles200Response model.
ListAccessProfiles200ResponseAccessProfilesInner model.
ListAccessProfiles200ResponseAccessProfilesInnerMcpServersInner model.
ListAccessProfiles200ResponseAccessProfilesInnerMcpToolGroupsInner model.
ListAccessProfiles200ResponseAccessProfilesInnerMcpToolOverridesInner model.
ListAccessProfiles200ResponseAccessProfilesInnerProviderConfigsInner model.
ListAccessProfiles200ResponseAccessProfilesInnerProviderConfigsInnerBudgetsInner model.
ListAccessProfiles200ResponseAccessProfilesInnerProviderConfigsInnerRateLimit model.
List budgets response
ListBuiltinPlugins200Response model.
Paginated list of teams assigned to a business unit
Paginated list of business units
Business unit summary as returned in list responses
ListCircuitBreakerPolicies200Response model.
ListCircuitBreakerPolicies200ResponsePoliciesInner model.
ListCircuitBreakerPolicies200ResponsePoliciesInnerCondition model.
ListCircuitBreakerPolicies200ResponsePoliciesInnerConditionSignalsInner model.
How long to keep the circuit open (in nanoseconds). Accepted as a Go duration string on write (e.g. "30s", "5m"); returned as an integer (nanoseconds) on read. Defaults to 30 seconds (30000000000 ns).
Response containing a list of files in a container
A file object within a container
ListContainers200Response model.
A container object
Expiration configuration for a container
List customers response
ListFolders200Response model.
Prompt folder
ListMcpToolGroups200Response model.
ListMcpToolGroups200ResponseMcpToolGroupsInner model.
ListMcpToolGroups200ResponseMcpToolGroupsInnerToolsInner model.
Response containing list of model configs
List model details response
Model details with capability metadata
ListModelDetailsManagement200ResponseModelsInnerArchitecture model.
List models response
Model information
ListModelsResponse model.
ListOperations200Response model.
List plugins response
ListPricingOverridesResponse model.
ListPromptSessions200Response model.
ListPromptVersions200Response model.
ListPrompts200Response model.
Prompt version (immutable snapshot)
Prompt playground session
Message within a prompt session
Prompt version (immutable snapshot)
Message within a prompt version
Response containing list of provider governance settings
Response for listing keys for a provider
List providers response
List rate limits response
ListResources200Response model.
ListResources200ResponseResourcesInner model.
ListRoles200Response model.
ListRoles200ResponseRolesInner model.
Response containing list of routing rules
ListSkillVersionsResponse model.
ListSkillsResponse model.
ListTeams200Response model.
ListTeams200ResponseTeamsInner model.
List teams response
ListUserAccessProfiles200Response model.
ListUserAccessProfiles200ResponseAccessProfilesInner model.
ListUsers200Response model.
ListUsers200ResponseUsersInner model.
Active or fallback user access profile, if assigned.
RBAC role details
ListUsers200ResponseUsersInnerTeamsInner model.
List virtual keys response
Log entry
Phase-scoped placeholder-to-original-value mappings for reversible redactions. Present only on log detail responses when the caller has Logs:Reveal.
Log statistics
Login request
Login response
Logout response
Error response
Authentication type for MCP connections: - none: No authentication - headers: Static header-based authentication (admin sets API keys / custom headers once, shared by all callers) - oauth: OAuth 2.0 authentication (server-level, admin authenticates once) - per_user_oauth: Per-user OAuth 2.0 authentication (each user authenticates individually) - per_user_headers: Per-user headers (each user submits their own header values; admin declares the schema)
Connected MCP client with its tools
Full MCP client configuration (used in responses)
Minimal MCP client view embedded in session rows.
Tool function definition
Per-virtual-key tool access configuration as returned in list/get responses
Response for GET /api/mcp/per-user-headers/flows/{id}. Carries the schema the end-user needs to fill in plus identity binding info for display.
Request body for PUT /api/mcp/per-user-headers/flows/{id}. The flow row identifies the (mode, identity, mcp_client) triple, so the caller carries only the values. Extra keys not in the live per_user_header_keys schema are dropped server-side.
McpHeadersSubmitResponse model.
Response for GET /api/oauth/per-user/flows/{id}. Mirrors the headers-side MCPHeadersFlowDetail — identity binding for display plus the bits the consent UI needs to decide its copy.
McpServerMessage200Response model.
JSON-RPC 2.0 request
McpServerMessageRequestId model.
Response for POST /api/mcp/sessions/{id}/reauth. Returns the URL the caller must visit to complete the fresh authentication / resubmission.
One row on the MCP Sessions list. Covers OAuth tokens, header credentials, and pending flows (of either kind). Always-set fields are at the top; per-kind-only fields use omitempty.
McpSessionsListResponse model.
Minimal user view embedded on user-keyed session rows.
Minimal virtual-key view embedded in session rows.
Simple message response
Model model.
Model configuration with budget and rate limit settings
Response containing a created/updated model config
ModelDefaultParameters model.
ModelPerRequestLimits model.
ModelPricing model.
AI model provider identifier
ModelTopProvider model.
Network configuration for provider connections
OAuth configuration for MCP client creation
Status of an OAuth configuration
Response when initiating an OAuth flow
OAuth access and refresh tokens
OcrDocument model.
OcrDocumentOneOf model.
OcrDocumentOneOf1 model.
OcrPage model.
Confidence scores for this page (present when confidence_scores_granularity is set)
OcrPageDimensions model.
OcrPageImage model.
OcrRequest model.
Format for bounding box annotations. Supports text, json_object, and json_schema modes.
JSON schema definition (required when type is json_schema)
OcrRequestBboxAnnotationFormatOneOf model.
OcrRequestBboxAnnotationFormatOneOf1 model.
OcrResponse model.
OcrUsageInfo model.
OpenAiChatRequest model.
OpenAiEmbeddingRequest model.
OpenAiListModelsResponse model.
OpenAiListModelsResponseDataInner model.
OpenAiMessage model.
OpenAiResponsesRequest model.
OpenAiResponsesRequestReasoning model.
OpenAiResponsesRequestText model.
OpenAiResponsesRequestTextFormat model.
OpenAiResponsesRequestTextFormatJsonSchema model.
OpenAiSpeechRequest model.
OpenAiTextCompletionRequest model.
OpenaiCreateImage200Response model.
Streaming response chunk for image generation (OpenAI format). Sent via Server-Sent Events (SSE) when stream=true.
OpenaiCreateImageRequest model.
Storage configuration for cloud storage backends
Google Cloud Storage configuration
AWS S3 storage configuration
Search result from Perplexity AI search
PerplexityVideoResult model.
Plugin configuration
Current plugin status including types array (only populated for active plugins)
A pricing override that applies custom rates to matching requests.
Request type for pricing override filtering. Stream variants are treated identically to their base type - specifying chat_completion covers both streaming and non-streaming chat requests.
PricingOverrideResponse model.
Pricing fields to override. Only non-zero/non-null fields are applied. All values are cost per unit in USD.
PropagateAccessProfile200Response model.
PropagateAccessProfileRequest model.
Provider-level governance settings (budget and rate limits)
Response containing provider governance settings
Provider configuration response
Custom provider configuration
Allowed request types for custom providers
Proxy configuration
Rate limit configuration
Recalculate cost request
Log search filters
Recalculate cost job status
RedeliverWebhookResponse model.
RerankDocument model.
RerankRequest model.
RerankResponse model.
RerankResult model.
Responses format response
Responses format - uses ResponsesToolMessage schema
ResponsesRequest model.
ResponsesRequestReasoning model.
ResponsesRequestStreamOptions model.
ResponsesRequestText model.
ResponsesRequestTextFormat model.
ResponsesRequestToolChoice model.
ResponsesRequestToolChoiceOneOf model.
ResponsesRequestToolChoiceOneOfToolsInner model.
ResponsesRequestToolsInner model.
ResponsesResponse model.
ResponsesResponseError model.
ResponsesResponseIncompleteDetails model.
RetrieveFile200Response model.
CEL-based routing rule for intelligent request routing
Global scope routing rule
Scoped routing rule (requires scope_id)
Response containing created/updated routing rule
A single weighted routing target within a routing rule
Search logs response
Pagination metadata for list responses
ShiftSkillVersionRequest model.
Skill repository entry and currently served version metadata.
SkillFile model.
File entry used when creating or updating a skill version.
SkillOrphanCleanupResponse model.
SkillResponse model.
Source backing for an attached skill file.
Immutable skill version snapshot.
SpeechRequest model.
SpeechRequestPronunciationDictionaryLocatorsInner model.
SpeechRequestVoice model.
SpeechRequestVoiceOneOfInner model.
SpeechResponse model.
SpeechResponseAlignment model.
StartPerUserOauthFlow200Response model.
Generic success response
Table key configuration
Environment variable configuration
Team configuration
Team operation response
TestWebhookRequest model.
TestWebhookResponse model.
TextCompletionRequest model.
TextCompletionResponse model.
TranscriptionResponse model.
TranscriptionResponseSegmentsInner model.
TranscriptionResponseWordsInner model.
Partial update. Omitted fields preserve the current value. rate_limit: null explicitly clears the existing rate limit; omitting the field preserves it. Update enforces size limits not enforced on create: max 100 provider_configs, max 100 budgets, max 50 tags.
UpdateAccessProfileRequestRateLimit model.
Update budget request
Business unit governance operation response
Business unit configuration with governance association
Update business unit governance request. Passing an empty budget or rate_limit object removes that governance component.
Update configuration request
Update customer request
UpdateFolderRequest model.
Partial update. - Scalar fields (name, description, enabled) preserve the current value when omitted. - Array fields are replace-on-send: whatever you provide becomes the new full value. To clear an attachment dimension, send an empty array.
Request to update an existing model config. Scope and scope_id are identity fields and cannot be changed.
Update plugin request
Request body for updating a pricing override. All fields are optional - omitted fields are merged from the existing record. The patch field is always replaced in full when provided.
UpdatePromptRequest model.
UpdatePromptSessionRequest model.
Request to update provider governance settings
Update provider request. Keys are managed separately via /api/providers/{provider}/keys.
Update rate limit request
UpdateRolePermissionsRequest model.
Partial update. Omitted fields preserve the current value. - description is a nullable string: omitting it preserves the existing description; sending an empty string clears it. - dac defaults to the existing value when omitted, preventing accidental scope escalation.
Request to update a routing rule (all fields optional; providing targets replaces all existing targets)
UpdateSkillRequest model.
UpdateTeamRequest model.
UpdateUserTeamsRequest model.
Update virtual key request
UpdateVirtualKeyRequestMcpConfigsInner model.
UpdateVirtualKeyRequestProviderConfigsInner model.
UploadSkillFileResponse model.
VertexRankRequest model.
VertexRankRequestRecordsInner model.
VideoDelete200Response model.
VideoGeneration200Response model.
Information about content that was filtered due to safety policies
VideoGeneration200ResponseVideosInner model.
VideoGenerationRequest model.
VideoList200Response model.
VideoList200ResponseDataInner model.
VideoList200ResponseDataInnerError model.
VideoRemixRequest model.
Virtual key configuration
MCP configuration for a virtual key
Provider configuration for a virtual key
Virtual key quota response (self-service, no admin auth required)
A virtual key budget with the actual per-model spend (from request logs) accumulated in its current cycle [last_reset, now]. The per-model totals reconcile with current_usage. The models list is empty when the logging plugin is not enabled.
One model's actual usage (from request logs) within a budget cycle
Per-model budgets and rate limit (with current usage) for a model governed under a virtual key
Virtual key operation response
One delivery attempt in an endpoint's history.
WebhookDeliveryList model.
WebhookDeliveryListPagination model.
Outcome of a single delivery attempt: - delivered: the receiver returned 2xx - retryable_failure: failed but will be retried - permanent_failure: failed in a way that is not retried - exhausted: retries were used up without success
A registered webhook endpoint. The signing secret is never included in this representation; custom header values are redacted.
A redacted secret-bearing value as returned in responses. The literal is masked ("<REDACTED>"); ref and type describe the original source when set.
WebhookEndpointList model.
Create or update body for a webhook endpoint. The signing secret is never accepted here — it is generated by the server and returned once at creation, and can only be changed through the rotate-secret endpoint.
Returned once when an endpoint is created or its secret is rotated. The secret is shown a single time and cannot be retrieved again.
A terminal async-job event a webhook endpoint can subscribe to: - async_job.completed: an async job finished successfully - async_job.failed: an async job finished with an error
WebhookStatusResponse model.
Helper functions for building Tesla requests