> ## Documentation Index > Fetch the complete documentation index at: https://docs.getbifrost.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get consolidated dashboard data > Returns every metric shown on the workspace dashboard in a single response: overview totals and histograms, provider usage, model rankings, dimension rankings (team, user, virtual key, customer, business unit), and MCP usage. Intended for external integrations that want the full dashboard in one call rather than orchestrating the individual endpoints. Accepts the same LLM filter parameters as the histogram and rankings endpoints, plus the MCP filter parameters (`tool_names`, `server_labels`) which apply to the `mcp` section. Filters are applied once and every section is computed against the same time window and bucket size. The request fails as a whole if any section cannot be computed, so the payload is always complete. ## OpenAPI ````yaml /openapi/openapi.json get /api/logs/dashboard openapi: 3.1.0 info: title: Bifrost API description: > Bifrost HTTP Transport API for AI model inference and gateway management. This API provides a unified interface for interacting with multiple AI providers including OpenAI, Anthropic, Bedrock, Gemini, and more through a single API, along with comprehensive management APIs for configuring and monitoring the gateway. ## API Structure ### Unified Inference API (`/v1/*`) The primary API using Bifrost's unified format. Model parameters use the format `provider/model` (e.g., `openai/gpt-4`, `anthropic/claude-3-opus`). ### Async Inference API (`/v1/async/*`) Submit inference requests for asynchronous execution. Returns a job ID immediately and allows polling for results. Supports all inference types except batches, files, and containers. ### Provider Integration APIs Native provider-format APIs for drop-in compatibility: - `/openai/*` - OpenAI-compatible API - `/anthropic/*` - Anthropic-compatible API - `/genai/*` - Google GenAI (Gemini) compatible API - `/bedrock/*` - AWS Bedrock compatible API - `/cohere/*` - Cohere compatible API ### Framework Integration APIs Multi-provider proxy endpoints for AI frameworks: - `/litellm/*` - LiteLLM proxy with all provider formats - `/langchain/*` - LangChain compatible endpoints - `/pydanticai/*` - PydanticAI compatible endpoints ### Management APIs (`/api/*`) APIs for managing and monitoring the Bifrost gateway: - `/api/config` - Configuration management - `/api/providers` - Provider and API key management - `/api/plugins` - Plugin management - `/api/governance/*` - Virtual keys, teams, customers, budgets, rate limits, routing rules, and pricing overrides - `/api/logs` - Log search and analytics - `/api/mcp/*` - MCP (Model Context Protocol) client management - `/api/session/*` - Authentication and session management - `/api/cache/*` - Cache management - `/health` - Health check endpoint ## Fallbacks Requests can include fallback models that will be tried if the primary model fails. version: 1.0.0 contact: name: Contact Us url: https://getmaxim.ai/bifrost license: name: Apache 2.0 url: https://opensource.org/licenses/Apache-2.0 servers: - url: '{baseUrl}' description: Your Bifrost instance variables: baseUrl: default: http://localhost:8080 description: Base URL of your Bifrost instance (e.g. https://bifrost.mycompany.com) security: - BearerAuth: [] - BasicAuth: [] - ApiKeyAuth: [] tags: - name: Models description: Model listing and information - name: Chat Completions description: Chat-based text generation - name: Text Completions description: Text completion generation - name: Responses description: OpenAI Responses API compatible endpoints - name: OCR description: Optical character recognition for documents and images - name: Rerank description: Document reranking by relevance to a query - name: Embeddings description: Text embedding generation - name: Images description: Image generations, editing, and variations - name: Videos description: Video generation and management - name: Audio description: Speech synthesis and transcription - name: Count Tokens description: Token counting utilities - name: Batch description: Batch processing operations - name: Files description: File management operations - name: Containers description: Container management operations - name: Async Jobs description: Asynchronous job submission and retrieval endpoints - name: Realtime description: Realtime WebSocket and WebRTC endpoints - name: OpenAI Integration description: OpenAI-compatible API endpoints (/openai/*) - name: Azure Integration description: Azure OpenAI integration endpoints - name: Anthropic Integration description: Anthropic-compatible API endpoints (/anthropic/*) - name: GenAI Integration description: Google GenAI (Gemini) compatible API endpoints (/genai/*) - name: Bedrock Integration description: AWS Bedrock compatible API endpoints (/bedrock/*) - name: Cohere Integration description: Cohere compatible API endpoints (/cohere/*) - name: LiteLLM Integration description: LiteLLM proxy endpoints with multi-provider support (/litellm/*) - name: LangChain Integration description: LangChain compatible endpoints with multi-provider support (/langchain/*) - name: PydanticAI Integration description: >- PydanticAI compatible endpoints with multi-provider support (/pydanticai/*) - name: Health description: Health check endpoints - name: Configuration description: Configuration management endpoints - name: Session description: Session and authentication endpoints - name: Providers description: Provider management endpoints - name: Plugins description: Plugin management endpoints - name: MCP description: Model Context Protocol endpoints - name: Governance description: Virtual keys, teams, and customers management - name: Logging description: Log search and management endpoints - name: Cache description: Cache management endpoints - name: Vault description: Vault secret management endpoints - name: Skills description: Skills Repository management, marketplace, and download endpoints - name: Audit Logs description: >- CADF-compliant audit log search, export, and signature verification endpoints paths: /api/logs/dashboard: get: tags: - Logging summary: Get consolidated dashboard data description: > Returns every metric shown on the workspace dashboard in a single response: overview totals and histograms, provider usage, model rankings, dimension rankings (team, user, virtual key, customer, business unit), and MCP usage. Intended for external integrations that want the full dashboard in one call rather than orchestrating the individual endpoints. Accepts the same LLM filter parameters as the histogram and rankings endpoints, plus the MCP filter parameters (`tool_names`, `server_labels`) which apply to the `mcp` section. Filters are applied once and every section is computed against the same time window and bucket size. The request fails as a whole if any section cannot be computed, so the payload is always complete. operationId: getDashboard parameters: - name: providers in: query description: Comma-separated list of providers to filter by schema: type: string - name: models in: query description: Comma-separated list of models to filter by schema: type: string - name: aliases in: query description: Comma-separated list of model aliases to filter by schema: type: string - name: status in: query description: Comma-separated list of statuses to filter by schema: type: string - name: objects in: query description: Comma-separated list of object types to filter by schema: type: string - name: selected_key_ids in: query description: Comma-separated list of selected key IDs to filter by schema: type: string - name: virtual_key_ids in: query description: Comma-separated list of virtual key IDs to filter by schema: type: string - name: team_ids in: query description: Comma-separated list of team IDs to filter by schema: type: string - name: customer_ids in: query description: Comma-separated list of customer IDs to filter by schema: type: string - name: user_ids in: query description: Comma-separated list of user IDs to filter by schema: type: string - name: business_unit_ids in: query description: Comma-separated list of business unit IDs to filter by schema: type: string - name: routing_rule_ids in: query description: Comma-separated list of routing rule IDs to filter by schema: type: string - name: routing_engine_used in: query description: Comma-separated list of routing engines to filter by schema: type: string - name: start_time in: query description: Start time filter (RFC3339 format) schema: type: string format: date-time - name: end_time in: query description: End time filter (RFC3339 format) schema: type: string format: date-time - name: period in: query description: Relative time period filter schema: type: string - name: min_latency in: query description: Minimum latency filter schema: type: number - name: max_latency in: query description: Maximum latency filter schema: type: number - name: min_tokens in: query description: Minimum tokens filter schema: type: integer - name: max_tokens in: query description: Maximum tokens filter schema: type: integer - name: min_cost in: query description: Minimum cost filter schema: type: number - name: max_cost in: query description: Maximum cost filter schema: type: number - name: missing_cost_only in: query description: Only show logs with missing cost schema: type: boolean - name: stop_reasons in: query description: Comma-separated list of stop reasons to filter by schema: type: string - name: cache_hit_types in: query description: Comma-separated list of cache hit types to filter by schema: type: string - name: parent_request_id in: query description: Parent request ID to filter by schema: type: string - name: metadata_ in: query description: Metadata filter where is the metadata key to match schema: type: string - name: content_search in: query description: Search in request/response content schema: type: string - name: tool_names in: query description: Comma-separated list of MCP tool names to filter the MCP section by schema: type: string - name: server_labels in: query description: >- Comma-separated list of MCP server labels to filter the MCP section by schema: type: string responses: '200': description: Dashboard data retrieved successfully content: application/json: schema: type: object description: > 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. properties: meta: type: object description: Parameters the dashboard data was computed with properties: generated_at: type: string format: date-time description: UTC time the response was assembled bucket_size_seconds: type: integer format: int64 description: >- Width of every histogram bucket, derived from the time range start_time: type: string format: date-time description: Resolved start of the queried range end_time: type: string format: date-time description: Resolved end of the queried range overview: type: object description: Overview tab metrics properties: stats: $ref: '#/components/schemas/LogStats' requests: type: object description: Time-bucketed request count histogram properties: buckets: type: array items: type: object description: Time-bucketed request count properties: timestamp: type: string format: date-time count: type: integer format: int64 success: type: integer format: int64 error: type: integer format: int64 bucket_size_seconds: type: integer format: int64 tokens: type: object description: Time-bucketed token usage histogram properties: buckets: type: array items: type: object description: Time-bucketed token usage properties: timestamp: type: string format: date-time prompt_tokens: type: integer format: int64 completion_tokens: type: integer format: int64 total_tokens: type: integer format: int64 bucket_size_seconds: type: integer format: int64 cost: type: object description: Time-bucketed cost histogram with model breakdown properties: buckets: type: array items: type: object description: Time-bucketed cost data with model breakdown properties: timestamp: type: string format: date-time total_cost: type: number by_model: type: object additionalProperties: type: number description: Cost breakdown by model name bucket_size_seconds: type: integer format: int64 models: type: array items: type: string description: List of models present in the histogram models: type: object description: Time-bucketed model usage histogram properties: buckets: type: array items: type: object description: >- Time-bucketed model usage with success/error breakdown properties: timestamp: type: string format: date-time by_model: type: object additionalProperties: type: object description: Usage statistics for a single model properties: total: type: integer format: int64 success: type: integer format: int64 error: type: integer format: int64 description: Usage breakdown by model name bucket_size_seconds: type: integer format: int64 models: type: array items: type: string latency: type: object description: Time-bucketed latency histogram properties: buckets: type: array items: type: object description: Time-bucketed latency percentiles properties: timestamp: type: string format: date-time avg_latency: type: number p90_latency: type: number p95_latency: type: number p99_latency: type: number total_requests: type: integer format: int64 bucket_size_seconds: type: integer format: int64 provider_usage: type: object description: Provider Usage tab metrics properties: cost: type: object description: Time-bucketed cost histogram with provider breakdown properties: buckets: type: array items: type: object description: Time-bucketed cost data with provider breakdown properties: timestamp: type: string format: date-time total_cost: type: number by_provider: type: object additionalProperties: type: number description: Cost breakdown by provider name bucket_size_seconds: type: integer format: int64 providers: type: array items: type: string tokens: type: object description: Time-bucketed token histogram with provider breakdown properties: buckets: type: array items: type: object description: >- Time-bucketed token usage with provider breakdown properties: timestamp: type: string format: date-time by_provider: type: object additionalProperties: type: object description: Token statistics for a single provider properties: prompt_tokens: type: integer format: int64 completion_tokens: type: integer format: int64 total_tokens: type: integer format: int64 description: Token usage breakdown by provider name bucket_size_seconds: type: integer format: int64 providers: type: array items: type: string latency: type: object description: >- Time-bucketed latency histogram with provider breakdown properties: buckets: type: array items: type: object description: >- Time-bucketed latency data with provider breakdown properties: timestamp: type: string format: date-time by_provider: type: object additionalProperties: type: object description: Latency statistics for a single provider properties: avg_latency: type: number p90_latency: type: number p95_latency: type: number p99_latency: type: number total_requests: type: integer format: int64 description: Latency breakdown by provider name bucket_size_seconds: type: integer format: int64 providers: type: array items: type: string model_rankings: type: object description: Model Rankings tab data properties: rankings: type: object description: Models ranked by usage with trend comparison properties: rankings: type: array items: allOf: - type: object description: >- Aggregated stats for a single model over the query period properties: model: type: string provider: type: string total_requests: type: integer format: int64 success_count: type: integer format: int64 success_rate: type: number total_tokens: type: integer format: int64 total_cost: type: number avg_latency: type: number - type: object properties: trend: type: object description: >- Percentage change versus the previous comparable period properties: has_previous_period: type: boolean requests_trend: type: number tokens_trend: type: number cost_trend: type: number latency_trend: type: number histogram: type: object description: Time-bucketed model usage histogram properties: buckets: type: array items: type: object description: >- Time-bucketed model usage with success/error breakdown properties: timestamp: type: string format: date-time by_model: type: object additionalProperties: type: object description: Usage statistics for a single model properties: total: type: integer format: int64 success: type: integer format: int64 error: type: integer format: int64 description: Usage breakdown by model name bucket_size_seconds: type: integer format: int64 models: type: array items: type: string dimension_rankings: type: object description: > Ranking tables keyed by dimension (`team`, `user`, `virtual_key`, `customer`, `business_unit`); each value is that dimension's rankings. additionalProperties: type: object description: Dimension values ranked by usage with trend comparison properties: rankings: type: array items: allOf: - type: object description: >- Aggregated usage for a single dimension value (team, user, virtual key, etc.) properties: id: type: string name: type: string total_requests: type: integer format: int64 total_tokens: type: integer format: int64 total_cost: type: number - type: object properties: trend: type: object description: >- Percentage change versus the previous comparable period properties: has_previous_period: type: boolean requests_trend: type: number tokens_trend: type: number cost_trend: type: number dimension: type: string description: Entity used to group dimension rankings enum: - team - customer - business_unit - user - virtual_key total_actual_requests: type: integer format: int64 description: > Distinct request count over the attributed population. Only set for fan-out dimensions (team, customer, business_unit) on Postgres. total_attributed_requests: type: integer format: int64 description: > Requests credited to every dimension value they touch; the sum can exceed the real request count. Only set for fan-out dimensions. mcp: type: object description: MCP usage tab metrics properties: volume: type: object description: Time-bucketed MCP tool call volume histogram properties: buckets: type: array items: type: object description: Time-bucketed MCP tool call volume properties: timestamp: type: string format: date-time count: type: integer format: int64 success: type: integer format: int64 error: type: integer format: int64 bucket_size_seconds: type: integer format: int64 cost: type: object description: Time-bucketed MCP cost histogram properties: buckets: type: array items: type: object description: Time-bucketed MCP cost data properties: timestamp: type: string format: date-time total_cost: type: number bucket_size_seconds: type: integer format: int64 top_tools: type: object description: Top MCP tools by call count (limit 10) properties: tools: type: array items: type: object description: Aggregated stats for a single MCP tool properties: tool_name: type: string count: type: integer format: int64 cost: type: number '400': description: Bad request content: application/json: schema: $ref: '#/components/schemas/BifrostError' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/BifrostError' security: - ManagementBearerAuth: [] components: schemas: LogStats: type: object description: Log statistics required: - total_requests - total_tokens - total_cost - average_latency - success_rate - user_facing_success_rate - user_facing_total_requests properties: total_requests: type: integer format: int64 total_tokens: type: integer format: int64 total_cost: type: number average_latency: type: number success_rate: type: number description: Percentage of completed provider attempts that succeeded user_facing_success_rate: type: number description: >- Percentage of user requests that ultimately succeeded, counting fallback chains as one request user_facing_total_requests: type: integer format: int64 description: >- Count of root requests used as the denominator for user_facing_success_rate cache_hit_rate_total_requests: type: integer format: int64 description: Completed requests used as the local-cache hit-rate denominator direct_cache_hits: type: integer format: int64 description: Number of direct local-cache hits semantic_cache_hits: type: integer format: int64 description: Number of semantic local-cache hits BifrostError: type: object description: Error response from Bifrost properties: event_id: type: string type: type: string is_bifrost_error: type: boolean status_code: type: integer error: $ref: '#/components/schemas/ErrorField' extra_fields: $ref: '#/components/schemas/BifrostErrorExtraFields' ErrorField: type: object properties: type: type: string code: type: string message: type: string param: type: string event_id: type: string BifrostErrorExtraFields: type: object properties: provider: $ref: '#/components/schemas/ModelProvider' model_requested: type: string request_type: type: string ModelProvider: type: string description: AI model provider identifier enum: - openai - azure - anthropic - bedrock - cohere - vertex - vllm - mistral - ollama - groq - sgl - parasail - perplexity - replicate - cerebras - deepseek - gemini - openrouter - elevenlabs - huggingface - nebius - xai - runway - fireworks securitySchemes: BearerAuth: type: http scheme: bearer description: > Bearer token authentication. Use your provider API key or Bifrost authentication token. Virtual keys (prefixed with `sk-bf-`) can also be passed here. BasicAuth: type: http scheme: basic description: | Basic authentication using username and password. ApiKeyAuth: type: apiKey in: header name: x-api-key description: | API key authentication via the `x-api-key` header. Virtual keys (prefixed with `sk-bf-`) can also be passed here. ManagementBearerAuth: type: http scheme: bearer description: > Management API authentication for `/api/*` endpoints. Use the `Authorization` header with `Bearer `. Virtual keys, dashboard/user/session tokens, and `x-api-key` headers are not supported on management APIs. ````