MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 6 callersMethodflush_and_get_aggregated_daily_spend_update_transactions
Get all updates from the queue and return all updates aggregated by daily_transaction_key. Works for both user and team spend updates.
litellm/proxy/db/db_transaction_queue/daily_spend_update_queue.py:91
↓ 6 callersFunctionflush_shadow_eval_funnel
(prisma_client: "PrismaClient")
litellm/proxy/db/shadow_eval_funnel.py:48
↓ 6 callersMethodfor_client
(cls, client: PrismaClient)
litellm/proxy/db/baseline_accounting.py:428
↓ 6 callersFunctionformatCompact
(value: number)
ui/litellm-dashboard/src/app/(dashboard)/usage/_components/components/overview/overviewData.ts:249
↓ 6 callersFunctionformatCost
(cost: number | null | undefined)
ui/litellm-dashboard/src/components/GuardrailsMonitor/usageUnits.ts:7
↓ 6 callersFunctionformat_base64_size
Return a human-readable byte-size estimate from a base64 character count.
litellm/_logging.py:333
↓ 6 callersFunctionformat_fallback_outcome_message
User-facing explanation appended when the fallback orchestrator gives up and re-raises the primary error.
litellm/litellm_core_utils/routing_common_utils.py:202
↓ 6 callersMethodfreeze
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 6 callersMethodfrom_client
(cls, client: object, *, cache: UserApiKeyCache | None = None)
litellm/proxy/agent_endpoints/identity_store.py:43
↓ 6 callersMethodfrom_config
(cls, config: RouterConfig, host: PythonHost = python_host)
litellm/router.py:252
↓ 6 callersMethodfrom_metadata
(cls, metadata: Mapping[str, object])
litellm/types/proxy/carried_budget_state.py:26
↓ 6 callersMethodfrom_wire
(self, value: object)
litellm/router_rust/surface/model_info.py:111
↓ 6 callersMethodfunction
(self)
litellm/proxy/hooks/litellm_skills/main.py:64
↓ 6 callersFunctiong
(t,a)
litellm/proxy/_experimental/out/_next/static/chunks/11et800l-khs-.js:1
↓ 6 callersFunctiongR
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 6 callersFunctiongated
(host: ScriptedHost, error: Exception | None = None)
tests/unit/test_router/core/test_gaps_l8400_precall.py:44
↓ 6 callersFunctiongated_capabilities_of
The licensed capabilities this deployment claims, or empty unless it is a complexity router.
litellm/router_strategy/auto_router/auto_router_model_naming.py:343
↓ 6 callersFunctiongateway_user_reader
(repository: ConfigRepository)
litellm/proxy/management_endpoints/roi_calculator_endpoints.py:299
↓ 6 callersFunctiongcs_part
(name: str, metadata: Mapping[str, JsonValue] | None = WIRE_METADATA)
tests/integration/caching/test_embedding_file_block_cache.py:40
↓ 6 callersFunctiongemini_model
(scenario: Scenario, url: str)
tests/integration/caching/test_embedding_file_block_cache.py:85
↓ 6 callersFunctiongenerate_iam_token
(api_key=None, **params)
litellm/llms/watsonx/common_utils.py:32
↓ 6 callersFunctiongenerate_key
(**kwargs: object)
tests/unit/proxy/management_helpers/test_bulk_user_creation.py:356
↓ 6 callersMethodgenerate_model_id
(model_group: str, litellm_params: dict)
litellm/router_deprecated.py:647
↓ 6 callersFunctionget
Sync: Get an interaction by its ID.
litellm/interactions/main.py:425
↓ 6 callersFunctiongetAuthHeaderName
()
ui/litellm-dashboard/src/lib/http/runtime.ts:44
↓ 6 callersFunctiongetBudgetDurationLabel
(value: string | null | undefined, t: TFunction = i18n.t.bind(i18n))
ui/litellm-dashboard/src/components/common_components/budget_duration_dropdown.tsx:59
↓ 6 callersFunctiongetEndpointType
(mode: string)
ui/litellm-dashboard/src/components/chat_ui/mode_endpoint_mapping.tsx:50
↓ 6 callersFunctiongetForecastConfigError
( value: ComplexityRouterConfigValue, t: TFunction = i18n.t.bind(i18n), )
ui/litellm-dashboard/src/components/add_model/forecast_classifier_config.ts:176
↓ 6 callersFunctiongetGuardrailProviders
()
ui/litellm-dashboard/src/app/(dashboard)/guardrails/_components/guardrail_info_helpers.tsx:76
↓ 6 callersFunctiongetKeywordTierRulesError
( keywordTierRules: KeywordTierRule[], rows: readonly TierRow[], t: TFunction = i18n.t.bind(i18n), )
ui/litellm-dashboard/src/components/add_model/build_complexity_router_config.ts:384
↓ 6 callersMethodgetMetaProperty
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 6 callersMethodgetPendingPromise
({getSearchParamsSnapshot:e=c})
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:2
↓ 6 callersFunctiongetPoliciesList
(accessToken: string)
ui/litellm-dashboard/src/components/networking.tsx:3657
↓ 6 callersFunctiongetProviderSpecificFields
(providerValue: string)
ui/litellm-dashboard/src/components/vector_store_providers.tsx:411
↓ 6 callersFunctiongetRouterSettingsCall
(accessToken: string)
ui/litellm-dashboard/src/components/networking.tsx:3026
↓ 6 callersMethodgetState
()
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 6 callersMethodgetStore
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 6 callersMethodgetType
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 6 callersFunctionget_active_mcp_request_ctx
()
litellm/proxy/mcp_server/mcp_context.py:23
↓ 6 callersMethodget_add
Returns add list, defaulting to empty list if not specified.
litellm/types/proxy/policy_engine/policy_types.py:157
↓ 6 callersMethodget_agent_card
Fetch the agent card, probing every known path when none is given.
litellm/a2a_protocol/card_resolver.py:220
↓ 6 callersMethodget_all_beta_headers
Get all beta headers from the anthropic provider config.
tests/unit/test_anthropic_beta_headers_filtering.py:60
↓ 6 callersMethodget_all_latest_health_checks
Latest health check per (model_id, model_name), deduplicated in Postgres.
litellm/proxy/utils.py:8332
↓ 6 callersMethodget_all_llm_api_params
Gets the supported kwargs for each call type and combines them. The result is derived from static type annotations and fixed sets, s
litellm/litellm_core_utils/model_param_helper.py:93
↓ 6 callersMethodget_all_spend_logs_for_previous_response_id
Get all spend logs for a previous response id SQL query SELECT session_id, api_key, "user", team_id FROM spend_logs WHERE
litellm/responses/litellm_completion_transformation/session_handler.py:602
↓ 6 callersMethodget_all_transactions_from_redis_buffer_pipeline
Drains the main 7 Redis buffer queues in a single pipeline round-trip. Returns a 7-tuple of parsed results in this order:
litellm/proxy/db/db_transaction_queue/redis_update_buffer.py:764
↓ 6 callersFunctionget_api_base
(api_base: str | None = None)
litellm/llms/gigachat/utils.py:24
↓ 6 callersMethodget_api_base
(self)
litellm/llms/chatgpt/authenticator.py:93
↓ 6 callersMethodget_async_custom_stream_wrapper
( self, model: str, custom_llm_provider: str, logging_obj: LiteLLMLoggingObj,
litellm/llms/oci/chat/transformation.py:799
↓ 6 callersFunctionget_auto_router_session
One auto-routed session, for the key that ran it: the model its last turn was routed to and the session's spend against the router's savings
litellm/proxy/management_endpoints/auto_router_endpoints.py:1041
↓ 6 callersMethodget_available_deployments
Returns a deployment with the lowest latency
litellm/router_strategy/lowest_latency.py:568
↓ 6 callersFunctionget_aws_arn_prefix
(aws_region_name: str | None)
litellm/litellm_core_utils/aws_partition.py:42
↓ 6 callersMethodget_aws_region_name
( self, optional_params: dict[str, object], # mutable-ok: mirrors override contract m
litellm/llms/bedrock/base_aws_llm.py:750
↓ 6 callersMethodget_azure_ai_route
Get the Azure AI route for the given model. Similar to BedrockModelInfo.get_bedrock_route(). Supported routes: - ag
litellm/llms/azure_ai/common_utils.py:227
↓ 6 callersFunctionget_azure_request_auth_headers
( headers: Mapping[str, str], azure_client_params: Mapping[str, object], )
litellm/llms/azure/common_utils.py:681
↓ 6 callersMethodget_base_azure_url
( cls, api_base: str | None, litellm_params: GenericLiteLLMParams | Mapping[str, objec
litellm/llms/azure/common_utils.py:1114
↓ 6 callersFunctionget_batch_from_database
Try to retrieve batch object from ManagedObjectTable for consistent state. Args: batch_id: The batch ID (may be unified/encoded)
litellm/proxy/openai_files_endpoints/common_utils.py:1522
↓ 6 callersMethodget_batch_id_from_vertex_ai_batch_response
Gets the batch id from the Vertex AI Batch response safely vertex response: `projects/510528649030/locations/us-central1/batchPredic
litellm/llms/vertex_ai/batches/transformation.py:281
↓ 6 callersFunctionget_bearer_token
( api_key: str, )
litellm/proxy/auth/user_api_key_auth.py:1239
↓ 6 callersMethodget_bedrock_count_tokens_endpoint
Construct the AWS Bedrock CountTokens API endpoint using existing LiteLLM functions. Args: model: The resolved model ID
litellm/llms/bedrock/count_tokens/transformation.py:222
↓ 6 callersFunctionget_bedrock_cross_region_inference_regions
Abbreviations of regions AWS Bedrock supports for cross region inference.
litellm/llms/bedrock/common_utils.py:1187
↓ 6 callersMethodget_cache_key
Get Redis cache key for a polling ID
litellm/proxy/response_polling/polling_handler.py:47
↓ 6 callersMethodget_cached_health_check_results
Get cached health check results from Redis. Returns: Optional[Dict]: Cached health check results or None if not found/ex
litellm/proxy/health_check_utils/shared_health_check_manager.py:126
↓ 6 callersFunctionget_category_yaml
Get the YAML or JSON content for a specific content filter category. Args: category_name: The name of the category (e.g., "bias_gend
litellm/proxy/guardrails/guardrail_endpoints.py:1575
↓ 6 callersFunctionget_chatgpt_auth_file
( litellm_params: "Mapping[str, object] | GenericLiteLLMParams | None", )
litellm/llms/chatgpt/authenticator.py:49
↓ 6 callersFunctionget_chatgpt_session_id
(litellm_params: object)
litellm/llms/chatgpt/common_utils.py:406
↓ 6 callersFunctionget_client_requested_model
(request: Request | None)
litellm/proxy/common_utils/http_parsing_utils.py:436
↓ 6 callersMethodget_combined_callback_list
(self, dynamic_success_callbacks: list | None, global_callbacks: list)
litellm/proxy/utils.py:2505
↓ 6 callersMethodget_complete_file_url
Get the complete url for the request
litellm/llms/vertex_ai/files/transformation.py:1242
↓ 6 callersMethodget_complete_url
( self, api_base: str | None, api_key: str | None, model: str, optiona
litellm/llms/langflow/chat/transformation.py:102
↓ 6 callersMethodget_complete_url
Build the Vertex AI Live WSS endpoint URL. If *api_base* is provided it overrides the default aiplatform host, allowing ente
litellm/llms/vertex_ai/realtime/transformation.py:61
↓ 6 callersMethodget_complete_url
Get the complete URL for Vertex AI TTS request Google Cloud TTS endpoint: https://texttospeech.googleapis.com/v1/text:synthesize
litellm/llms/vertex_ai/text_to_speech/transformation.py:748
↓ 6 callersMethodget_complete_url
( self, api_base: str | None, optional_params: dict[str, object], data: dict[s
litellm/llms/tinyfish/search/transformation.py:72
↓ 6 callersMethodget_complete_url
Construct complete Watsonx URL with version parameter. This ensures the version parameter is ALWAYS included in the URL, sol
litellm/llms/watsonx/passthrough/transformation.py:19
↓ 6 callersMethodget_configured_mode
(self, model_name: str)
litellm/router_deprecated.py:597
↓ 6 callersFunctionget_content_from_model_response
Gets content from model response
litellm/litellm_core_utils/prompt_templates/common_utils.py:598
↓ 6 callersFunctionget_copilot_default_headers
Get default headers for GitHub Copilot Responses API. Based on copilot-api's header configuration.
litellm/llms/github_copilot/common_utils.py:49
↓ 6 callersMethodget_count_tokens_endpoint
Get the Azure AI Anthropic CountTokens API endpoint. Args: api_base: The Azure AI API base URL (e.
litellm/llms/azure_ai/anthropic/count_tokens/transformation.py:88
↓ 6 callersMethodget_data
Check if key valid
litellm/proxy/db/base_client.py:12
↓ 6 callersFunctionget_datadog_source
()
litellm/integrations/datadog/datadog_handler.py:12
↓ 6 callersFunctionget_default_headers
Get default headers for HTTP requests. - Default: `User-Agent: litellm/{version}` - Override: set `LITELLM_USER_AGENT` to fully override
litellm/llms/custom_httpx/http_handler.py:183
↓ 6 callersFunctionget_docs_url
Get the docs (Swagger UI) URL from the environment variables. - If DOCS_URL is set, return it. - If NO_DOCS is True, return None. -
litellm/proxy/utils.py:9771
↓ 6 callersFunctionget_env_float
Float counterpart of `get_env_int`.
litellm/litellm_core_utils/env_utils.py:62
↓ 6 callersFunctionget_excluded_filtered_deployments
Filter out deployments whose `model_info.id` appears in `excluded_deployment_ids`. Used by weighted-routing failover so a single logical req
litellm/utils.py:6441
↓ 6 callersMethodget_file_content
Fetch the content of a file from the BitBucket repository. Args: file_path: Path to the file in the repository
litellm/integrations/bitbucket/bitbucket_client.py:132
↓ 6 callersMethodget_guardrail_bearer_token
(headers: Headers, auth: UserAPIKeyAuth)
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:1871
↓ 6 callersMethodget_guardrail_from_metadata
Returns the guardrail(s) to be run from the root, else from both metadata fields together
litellm/integrations/custom_guardrail.py:963
↓ 6 callersFunctionget_guardrail_ui_settings
Get the UI settings for the guardrails Returns: - Supported entities for guardrails - Supported modes for guardrails - PII entit
litellm/proxy/guardrails/guardrail_endpoints.py:1508
↓ 6 callersMethodget_health_check_lock_key
Get the Redis key for health check lock.
litellm/proxy/health_check_utils/shared_health_check_manager.py:59
↓ 6 callersMethodget_hierarchical_router_settings
( self, user_api_key_dict: UserAPIKeyAuth | None, prisma_client: PrismaClient | None,
litellm/proxy/proxy_server.py:8300
↓ 6 callersMethodget_id
(self, user_info: CallInfo)
litellm/integrations/SlackAlerting/budget_alert_types.py:31
↓ 6 callersFunctionget_in_flight_requests
Module-level convenience wrapper used by the /health/backlog endpoint.
litellm/proxy/middleware/in_flight_requests_middleware.py:88
↓ 6 callersMethodget_input_limits
( self, model: str, custom_llm_provider: str, headers: Mapping[str, str] )
litellm/llms/base_llm/decisions/transformation.py:553
↓ 6 callersMethodget_instance
Find the PrometheusLogger instance from litellm.callbacks, if registered.
litellm/integrations/prometheus.py:499
↓ 6 callersFunctionget_litellm_code_execution_tool
Returns the litellm_code_execution tool definition in OpenAI format. This tool enables automatic code execution in a sandboxed environment
litellm/llms/litellm_proxy/skills/code_execution.py:133
↓ 6 callersFunctionget_mcp_jwt_signer
Return the active MCPJWTSigner singleton, or None if not initialized.
litellm/proxy/guardrails/guardrail_hooks/mcp_jwt_signer/mcp_jwt_signer.py:142
↓ 6 callersMethodget_microsoft_callback_response
Get the Microsoft SSO callback response, with the IdP identity assertion the token response carried (the id_token and refresh token a
litellm/proxy/management_endpoints/ui_sso.py:4707
↓ 6 callersFunctionget_model_rate_limit_from_metadata
( user_api_key_dict: UserAPIKeyAuth, metadata_accessor_key: Literal["team_metadata", "organization_met
litellm/proxy/auth/auth_utils.py:1665
↓ 6 callersFunctionget_new_token
(data: RegenerateKeyRequest | None)
litellm/proxy/management_endpoints/key_management_endpoints.py:6178
↓ 6 callersMethodget_object
(self, *, Bucket: str, Key: str)
litellm/litellm_core_utils/get_model_cost_map.py:282
← previousnext →13,001–13,100 of 202,479, ranked by callers