MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 5 callersMethodget_activity
(self, start_date: str, end_date: str)
litellm/models/gateway_activity.py:31
↓ 5 callersMethodget_agent_by_name
The agent registered under ``agent_name``, if any.
litellm/proxy/auth/handle_jwt.py:194
↓ 5 callersFunctionget_agent_card_url
Return the agent endpoint URL from the resolved SDK card.
litellm/a2a_protocol/card_resolver.py:153
↓ 5 callersMethodget_aggregated_window_spend_transactions
Sum spend per (entity_type, entity_id, window_duration, window_start). Increments belonging to different windows stay separate even when they
litellm/proxy/db/db_transaction_queue/window_spend_update_queue.py:179
↓ 5 callersFunctionget_all_access_groups_from_db
Get all access groups from the database. Returns: Dict[str, AccessGroupInfo]: Dictionary mapping access_group name to info
litellm/proxy/management_endpoints/model_access_group_management_endpoints.py:756
↓ 5 callersMethodget_all_jwt_team_ids
Return team IDs from both the plural ``team_ids_jwt_field`` and the singular ``team_id_jwt_field`` claim (string or list of strings),
litellm/proxy/auth/handle_jwt.py:432
↓ 5 callersMethodget_all_policies_from_db
Get all policies from the database, optionally filtered by version_status. Args: prisma_client: The Prisma client instan
litellm/proxy/policy_engine/policy_registry.py:619
↓ 5 callersMethodget_all_search_tools_from_db
Get all search tools from the database. Args: prisma_client: Prisma client instance Returns: List o
litellm/proxy/search_endpoints/search_tool_registry.py:341
↓ 5 callersMethodget_allowed_agents_for_key
Get allowed agents for a key. 1. First checks native key-level agent permissions (object_permission) 2. Also includes agents
litellm/proxy/agent_endpoints/auth/agent_permission_handler.py:331
↓ 5 callersMethodget_allowed_mcp_servers_for_agent
Get allowed MCP servers for an agent (from the agent's object_permission). Returns the agent's direct servers, the servers in its ac
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:4533
↓ 5 callersFunctionget_api_base
Returns the api base used for calling the model. Parameters: - model: str - the model passed to litellm.completion() - optional_para
litellm/litellm_core_utils/llm_response_utils/get_api_base.py:30
↓ 5 callersMethodget_api_base
(self, api_base: str | None, **kwargs: object)
litellm/llms/azure/realtime/http_transformation.py:27
↓ 5 callersMethodget_api_base
(self, api_base: str | None, **kwargs)
litellm/llms/openai/realtime/http_transformation.py:10
↓ 5 callersMethodget_api_base
Return the Copilot API endpoint for a stored token without starting device flow.
litellm/llms/github_copilot/authenticator.py:193
↓ 5 callersMethodget_api_key
Return the stored GitHub access token, loading it with device flow when needed.
litellm/llms/github_copilot/authenticator.py:189
↓ 5 callersFunctionget_api_key_from_env
()
litellm/llms/gemini/common_utils.py:510
↓ 5 callersMethodget_assistant_content_message
(self, parts: list[HttpxPartType])
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:2104
↓ 5 callersFunctionget_authorized_resources_from_key_access_groups
For each access_group_id on the key, fetch the LiteLLM_AccessGroupTable row and contribute its `resource_field` only if the group authorizes
litellm/proxy/auth/auth_checks.py:5791
↓ 5 callersFunctionget_auto_router_benchmarks
Benchmarks for the auto-router dashboard: session shape, savings against the configured baseline, and prompt-caching behaviour bucketed by wh
litellm/proxy/management_endpoints/auto_router_endpoints.py:959
↓ 5 callersFunctionget_autorouter_presets
( url: str, fetch: Callable[[str], Awaitable[Mapping[str, AutoRouterPresetRecord]]] = _fetch_remote_au
litellm/proxy/public_endpoints/public_endpoints.py:605
↓ 5 callersFunctionget_azure_ad_token_from_username_password
Get Azure AD token provider from `client_id`, `azure_username`, and `azure_password` Args: client_id: str azure_username: st
litellm/llms/azure/common_utils.py:376
↓ 5 callersFunctionget_azure_credentials
Resolve Azure credentials from params, litellm globals, and env vars.
litellm/llms/azure/common_utils.py:1176
↓ 5 callersFunctionget_azure_image_generation_config
(model: str)
litellm/llms/azure/image_generation/__init__.py:16
↓ 5 callersFunctionget_bedrock_image_edit_config_for_model
Return the correct Bedrock image-edit config for the model id. Same routing as ``BedrockImageEdit.get_config_class``: Stability edit models,
litellm/llms/bedrock/image_edit/amazon_nova_canvas_image_edit_transformation.py:512
↓ 5 callersFunctionget_bedrock_stream_event_statuses
Every modeled Bedrock stream event type mapped to its error status (None for a content event).
litellm/llms/bedrock/common_utils.py:2441
↓ 5 callersFunctionget_billed_token_rates
Rates the cost calculator bills ``usage`` at, resolved exactly as the totals and the token-type breakdown resolve them. None when the model's pric
litellm/litellm_core_utils/llm_cost_calc/utils.py:1930
↓ 5 callersFunctionget_byok_www_authenticate
()
litellm/proxy/mcp_server/oauth_utils.py:219
↓ 5 callersMethodget_cache
(self, key: str)
litellm/proxy/hooks/model_budget_shared_windows.py:33
↓ 5 callersMethodget_cache
(self, key, **kwargs)
litellm/caching/in_memory_cache.py:229
↓ 5 callersMethodget_cache
(self, key: str, loop_bound: bool = True, **kwargs)
litellm/caching/llm_caching_handler.py:68
↓ 5 callersMethodget_cache
(self, key, **kwargs)
tests/unit/proxy/test_redis_auth_cache_flag.py:51
↓ 5 callersMethodget_cache
(self, key, **kwargs)
tests/unit/caching/test_dual_cache.py:545
↓ 5 callersMethodget_cache_key
Generate a unique cache key based on the credential arguments.
litellm/llms/bedrock/base_aws_llm.py:223
↓ 5 callersFunctionget_cache_settings
Get cache configuration and available settings. Returns: - fields: List of all configurable cache settings with their metadata (type, de
litellm/proxy/management_endpoints/cache_settings_endpoints.py:454
↓ 5 callersFunctionget_cached_byok_credential
(user_id: str, server_id: str)
litellm/proxy/mcp_server/byok_credential_cache.py:27
↓ 5 callersFunctionget_cached_model_info
Lazy import and cache get_model_info to avoid circular imports. This function is used by bedrock transformation classes that need get_model_
litellm/llms/bedrock/common_utils.py:205
↓ 5 callersMethodget_cached_openai_client
Retrieves the OpenAI client from the in-memory cache based on the client initialization parameters
litellm/llms/openai/common_utils.py:341
↓ 5 callersFunctionget_cached_temporary_mcp_server
( server_id: str, )
litellm/proxy/management_endpoints/mcp_management_endpoints.py:657
↓ 5 callersMethodget_caller_identity
(self)
tests/unit/llms/bedrock/test_base_aws_llm.py:2371
↓ 5 callersFunctionget_caller_team_role
( team_table: LiteLLM_TeamTableCachedObj, user_api_key_dict: UserAPIKeyAuth, )
litellm/proxy/management_endpoints/key_management_endpoints.py:608
↓ 5 callersMethodget_chat_completion_prompt
Strip litellm_agent/ prefix from model name. Returns: (resolved_model, messages, non_default_params)
litellm/integrations/litellm_agent/litellm_agent_model_resolver.py:25
↓ 5 callersMethodget_complete_url
Get the complete URL for Azure Anthropic /v1/messages endpoint. Azure Foundry endpoint format: https://<resource-name>.services.ai.az
litellm/llms/azure_ai/anthropic/messages_transformation.py:78
↓ 5 callersMethodget_complete_url
( self, api_base: str | None, api_key: str | None, model: str, optiona
litellm/llms/predibase/chat/transformation.py:320
↓ 5 callersMethodget_complete_url
Get complete API URL for chat completions.
litellm/llms/gigachat/passthrough/transformation.py:32
↓ 5 callersMethodget_complete_url
Get complete URL for OpenAI Evals API
litellm/llms/openai/evals/transformation.py:60
↓ 5 callersMethodget_complete_url
Get the complete URL for PG vector service endpoints
litellm/llms/pg_vector/vector_stores/transformation.py:53
↓ 5 callersMethodget_complete_url
( self, api_base: str | None, api_key: str | None, model: str, optiona
litellm/llms/tencent/chat/transformation.py:131
↓ 5 callersMethodget_complete_url
( self, api_base: str | None, api_key: str | None, model: str, optiona
litellm/llms/tencent/messages/transformation.py:65
↓ 5 callersMethodget_complete_url
Get the complete URL for Manus Files API endpoint. Returns: str: The full URL for the Manus /v1/files endpoint
litellm/llms/manus/files/transformation.py:123
↓ 5 callersMethodget_complete_vertex_url
( self, custom_api_base: str | None, vertex_location: str | None, vertex_proje
litellm/llms/vertex_ai/vertex_llm_base.py:349
↓ 5 callersFunctionget_config_file_path
Get the path to the persistent CLI config file
litellm/proxy/client/cli/commands/config.py:23
↓ 5 callersFunctionget_config_value
Get a single value from the persistent CLI config
litellm/proxy/client/cli/commands/config.py:53
↓ 5 callersMethodget_configured_display_name
(self, model_name: str)
litellm/router_deprecated.py:593
↓ 5 callersMethodget_content
(self, metadata: PluginArchiveMetadata)
litellm/models/plugin_upload.py:168
↓ 5 callersFunctionget_cost_for_anthropic_web_search
Get the cost of using a web search tool for Anthropic.
litellm/llms/anthropic/cost_calculation.py:98
↓ 5 callersMethodget_cost_for_computer_use
Calculate cost for computer use feature. Azure: $0.003 USD per 1K input tokens, $0.012 USD per 1K output tokens
litellm/litellm_core_utils/llm_cost_calc/tool_call_cost_tracking.py:769
↓ 5 callersMethodget_cost_for_web_search
If request includes `web_search_options`, calculate the cost of the web search.
litellm/litellm_core_utils/llm_cost_calc/tool_call_cost_tracking.py:666
↓ 5 callersFunctionget_cost_for_web_search_request
Get the cost for a web search request for a given model. Args: custom_llm_provider: The custom LLM provider. usage: The usag
litellm/llms/__init__.py:51
↓ 5 callersMethodget_credentials
(self)
litellm/_redis_credential_provider.py:121
↓ 5 callersFunctionget_credentials_for_model
Retrieve API credentials for a model from the LLM Router. Does not check whether the caller may use ``model_id``; use ``get_authorized_c
litellm/proxy/openai_files_endpoints/common_utils.py:442
↓ 5 callersFunctionget_custom_llm_provider
( model: &'a str, custom_llm_provider: Option<&'a str>, )
litellm-rust/crates/core-utils/src/get_llm_provider_logic.rs:45
↓ 5 callersMethodget_custom_loggers_for_type
( self, callback_type: type[CustomLogger] )
tests/unit/test_router/core/scripted_host.py:236
↓ 5 callersMethodget_deployment_credentials
(self, model_id: str)
litellm/router_deprecated.py:626
↓ 5 callersFunctionget_deployment_successes_for_current_minute
Returns the number of successes for the current minute for a deployment_id Returns 0 if no value found
litellm/router_utils/router_callbacks/track_deployment_metrics.py:78
↓ 5 callersFunctionget_env_int_or_none
Parse an environment variable as an integer, returning None when it is unset, blank or unparsable. Use this instead of `get_env_int` when callers
litellm/litellm_core_utils/env_utils.py:37
↓ 5 callersFunctionget_error_message_str
(e: Exception)
litellm/proxy/utils.py:9731
↓ 5 callersFunctionget_fallback_errors_from_headers
( additional_headers: dict[str, object], )
litellm/litellm_core_utils/add_retry_fallback_headers.py:267
↓ 5 callersMethodget_fallback_model_within_budget
(self, user_api_key_dict: UserAPIKeyAuth, model: str)
litellm/proxy/auth/user_api_key_auth.py:418
↓ 5 callersFunctionget_fedramp_uplift_multiplier
Resolve the per-model uplift multiplier for the OpenAI FedRAMP endpoint. OpenAI applies a flat percentage uplift (e.g. +10%) on all token co
litellm/litellm_core_utils/llm_cost_calc/utils.py:1452
↓ 5 callersFunctionget_file_type_from_extension
(extension: str)
litellm/types/files.py:164
↓ 5 callersMethodget_final_response_obj
Get final response object after redacting the message input/output from logging
litellm/litellm_core_utils/litellm_logging.py:7263
↓ 5 callersFunctionget_fireworks_session_id
Session id to send as `x-session-affinity`, or None when the caller gave none. Deliberately does not fall back to `litellm_trace_id`, and ig
litellm/llms/fireworks_ai/common_utils.py:18
↓ 5 callersFunctionget_formatted_prompt
Extracts the prompt from the input data based on the call type. Returns a string.
litellm/litellm_core_utils/llm_response_utils/get_formatted_prompt.py:4
↓ 5 callersMethodget_fully_blocked_model_names
(self)
litellm/router_deprecated.py:685
↓ 5 callersFunctionget_gateway_daily_activity
Successful and failed gateway requests, counted at the ASGI edge. Deployment-wide: the underlying table has no per-key or per-user dimension
litellm/proxy/management_endpoints/gateway_request_endpoints.py:85
↓ 5 callersFunctionget_guardrail_submission
Get a single guardrail submission by id. Non-admins may only access submissions for teams they belong to.
litellm/proxy/guardrails/guardrail_endpoints.py:1029
↓ 5 callersFunctionget_hidden_params_storage
(obj: object)
litellm/litellm_core_utils/hidden_params.py:104
↓ 5 callersMethodget_http_method
Brave Search API uses GET requests for search.
litellm/llms/brave/search/transformation.py:108
↓ 5 callersFunctionget_image_type
take an image (really only the first ~100 bytes max are needed) and return 'png' 'gif' 'jpeg' 'webp' 'heic' or None. method added to allow dep
litellm/litellm_core_utils/token_counter.py:230
↓ 5 callersMethodget_internal_user_header_from_mapping
(user_header_mapping)
litellm/proxy/litellm_pre_call_utils.py:1876
↓ 5 callersMethodget_jwks
Return the JWKS for the RSA public key. Used by GET /.well-known/jwks.json so MCP servers can verify tokens.
litellm/proxy/guardrails/guardrail_hooks/mcp_jwt_signer/mcp_jwt_signer.py:396
↓ 5 callersFunctionget_key_own_model_rate_limit
( user_api_key_dict: UserAPIKeyAuth, rate_limit_key: Literal["model_rpm_limit", "model_tpm_limit"], )
litellm/proxy/auth/auth_utils.py:1376
↓ 5 callersFunctionget_litellm_code_execution_tool_anthropic
Returns the litellm_code_execution tool definition in Anthropic/messages API format. This tool enables automatic code execution in a sandbox
litellm/llms/litellm_proxy/skills/code_execution.py:154
↓ 5 callersMethodget_mcp_server_by_identifier
(self, identifier: str, client_ip: str | None = None)
litellm/proxy/mcp_server/mcp_server_manager.py:7536
↓ 5 callersMethodget_mcp_server_from_tool_name
Get the MCP Server from the tool name (handles both prefixed and non-prefixed names) Args: tool_name: Tool name (can be
litellm/proxy/mcp_server/mcp_server_manager.py:7295
↓ 5 callersMethodget_message
(self, *, ignore_subscribe_messages: bool, timeout: float)
litellm/proxy/common_utils/config_sync_pubsub.py:22
↓ 5 callersMethodget_model_cost_information
( base_model: str | None, custom_pricing: bool | None, custom_llm_provider: str | None
litellm/litellm_core_utils/litellm_logging.py:7211
↓ 5 callersMethodget_model_group_io_token_usage
Returns current ITPM/OTPM usage for a model group (sum across deployments).
litellm/router_rust/surface/model_info.py:829
↓ 5 callersMethodget_model_info
( self, model: str, api_base: str | None = None, api_key: str | None = None,
litellm/llms/lemonade/chat/transformation.py:184
↓ 5 callersFunctionget_models_from_access_groups
Collect model names from unified access groups. Models are matched by model name for backwards compatibility.
litellm/proxy/auth/auth_checks.py:4803
↓ 5 callersMethodget_models_from_db
Fetch all model deployments from the DB. Returns: - list: the rows (may be empty if no models exist) - None: signals
litellm/proxy/proxy_server.py:8890
↓ 5 callersMethodget_native_session_id
(self, state: PiStreamState)
litellm/llms/pi/harness/transformation.py:549
↓ 5 callersMethodget_newrelic_logger_for_request
Get a team-scoped NewRelicMetricsLogger for a given request. Resolves and caches per-team NewRelicMetricsLogger instances using
litellm/integrations/newrelic/newrelic_team_handler.py:28
↓ 5 callersMethodget_oauth2_headers_from_headers
Get the oauth2 headers from the request headers.
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:1896
↓ 5 callersMethodget_oauth_m2m_token
( self, api_base: str, client_id: str, client_secret: str, )
litellm/llms/databricks/common_utils.py:301
↓ 5 callersMethodget_objects
Get user, org, end-user, and team-membership objects. Returns ``(..., effective_user_id)``: JWT claim unless fuzzy lookup matched a l
litellm/proxy/auth/handle_jwt.py:1877
↓ 5 callersFunctionget_openapi_url
Get the OpenAPI JSON URL from the environment variables. - If OPENAPI_URL is set, return it. - If NO_OPENAPI is True, return None. -
litellm/proxy/utils.py:9791
↓ 5 callersMethodget_org_id
(self, token: dict, default_value: str | None)
litellm/proxy/auth/handle_jwt.py:714
↓ 5 callersMethodget_parent_request_tags
Tags from the parent LLM request, using the same extraction logic as standard logging (incl. User-Agent).
litellm/responses/mcp/litellm_proxy_mcp_handler.py:128
↓ 5 callersFunctionget_password_policy
(general_settings: Mapping[str, object])
litellm/proxy/auth/password_policy.py:74
← previousnext →15,901–16,000 of 202,479, ranked by callers