Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/BerriAI/litellm
/ functions
Functions
202,479 in github.com/BerriAI/litellm
⨍
Functions
202,479
◇
Types & classes
26,341
↳
Endpoints
5,595
↓ 9 callers
Method
get_agent_list
(self, agent_names: Sequence[str] | None = None)
litellm/proxy/agent_endpoints/agent_registry.py:439
↓ 9 callers
Function
get_anthropic_beta_from_headers
Extract anthropic-beta header values and convert them to a list. Supports both JSON array format and comma-separated values from user headers
litellm/llms/bedrock/common_utils.py:2562
↓ 9 callers
Method
get_arize_config
Helper function to get Arize configuration. Returns: ArizeConfig: A Pydantic model containing Arize configuration.
litellm/integrations/arize/arize.py:177
↓ 9 callers
Function
get_base_model_from_litellm_call_metadata
( metadata: Mapping[str, object] | None, )
litellm/litellm_core_utils/get_litellm_params.py:155
↓ 9 callers
Function
get_batch_id_from_unified_batch_id
(file_id: str)
litellm/proxy/openai_files_endpoints/common_utils.py:218
↓ 9 callers
Method
get_cache
( self, key: object, parent_otel_span: "Span | None" = None, local_only: bool = False )
litellm/router_rust/core.py:1309
↓ 9 callers
Function
get_cimd_client_id
(server: "MCPServer")
litellm/proxy/mcp_server/oauth_utils.py:208
↓ 9 callers
Method
get_combined_tool_content
( self, tool_call_chunks: Sequence["_ToolCallChunk"] )
litellm/litellm_core_utils/streaming_chunk_builder_utils.py:594
↓ 9 callers
Method
get_config
(cls)
litellm/llms/maritalk.py:42
↓ 9 callers
Function
get_config_from_bucket
( *, bucket_type: str | None, bucket_name: str, object_key: str, )
litellm/proxy/common_utils/load_config_utils.py:182
↓ 9 callers
Function
get_coordination_redis_settings
Get the coordination Redis configuration and available settings. Returns: - values: current coordination Redis settings, with password/s
litellm/proxy/management_endpoints/coordination_redis_endpoints.py:299
↓ 9 callers
Method
get_count
Return the number of HTTP requests currently in-flight.
litellm/proxy/middleware/in_flight_requests_middleware.py:59
↓ 9 callers
Function
get_datadog_hostname
()
litellm/integrations/datadog/datadog_handler.py:20
↓ 9 callers
Method
get_event_model_class
Returns the appropriate event model class based on the event type. Args: event_type (str): The type of event from the re
litellm/llms/openai/responses/transformation.py:1144
↓ 9 callers
Method
get_generic_sso_redirect_response
Get the redirect response for Generic SSO
litellm/proxy/management_endpoints/ui_sso.py:3451
↓ 9 callers
Function
get_log_team_lookup
Bind infrastructure without performing permission I/O before the handler's checks.
litellm/proxy/auth/authorization_dependencies.py:45
↓ 9 callers
Method
get_matching_policies
Get list of policy names that match the given context via attachments. Args: context: The request context to match again
litellm/proxy/policy_engine/policy_matcher.py:97
↓ 9 callers
Method
get_model_config
Factory method to get the appropriate embedding config based on model type Args: model: The model name, optionally prefi
litellm/llms/sagemaker/embedding/transformation.py:49
↓ 9 callers
Function
get_model_id_from_unified_batch_id
Get the model_id from the file_id Expected format: litellm_proxy;model_id:{};llm_batch_id:{};llm_output_file_id:{}
litellm/proxy/openai_files_endpoints/common_utils.py:202
↓ 9 callers
Method
get_model_info
curl http://localhost:11434/api/show -d '{ "name": "mistral" }'
litellm/llms/ollama/completion/transformation.py:292
↓ 9 callers
Method
get_model_info_with_id
Common logic across add + delete router models Parameters: - deployment - db_model -> flag for differentiating model
litellm/proxy/proxy_server.py:7845
↓ 9 callers
Method
get_openai_client
( self, api_key: str | None, api_base: str | None, timeout: float | httpx.Time
litellm/llms/openai/openai.py:2399
↓ 9 callers
Function
get_openai_credentials
Resolve OpenAI credentials from params, litellm globals, and env vars.
litellm/llms/openai/common_utils.py:503
↓ 9 callers
Method
get_or_compute
The cached token for `cache_key`, minting one when absent. `fingerprint` lets a caller address a slot by something stable (a principal) while
litellm/proxy/mcp_server/outbound_credentials/token_endpoint.py:152
↓ 9 callers
Function
get_potential_model_names
(model: str, custom_llm_provider: str | None)
litellm/utils.py:7075
↓ 9 callers
Method
get_provider_container_config
( provider: LlmProviders, )
litellm/utils.py:11353
↓ 9 callers
Method
get_provider_decisions_config
(model: str, provider: LlmProviders)
litellm/utils.py:10372
↓ 9 callers
Method
get_secret
(self, secret_name: str)
litellm/secret_managers/secret_manager_handler.py:63
↓ 9 callers
Function
get_shadow_eval_job
One job with derived counts, judge spend, latest error, and stratified results.
litellm/proxy/management_endpoints/auto_router_endpoints.py:1982
↓ 9 callers
Function
get_shared_realtime_ssl_context
Lazily create the SSL context reused by realtime websocket clients so we avoid import-order cycles during startup while keeping a single shar
litellm/llms/custom_httpx/http_handler.py:486
↓ 9 callers
Method
get_streaming_scan_key
(self, responses_so_far: Sequence[object])
litellm/llms/openai/responses/guardrail_translation/handler.py:1710
↓ 9 callers
Method
get_supported_event_hooks
(cls)
tests/unit/proxy/guardrails/guardrail_hooks/test_conduct.py:45
↓ 9 callers
Method
get_supported_openai_params
(self, model: str)
litellm/llms/anthropic/chat/transformation.py:879
↓ 9 callers
Method
get_supported_openai_params
(self, model: str)
litellm/llms/fireworks_ai/chat/transformation.py:250
↓ 9 callers
Function
get_tags_from_request_kwargs
Helper to get tags from request kwargs Args: request_kwargs: The request kwargs to get tags from metadata_variable_name: Whi
litellm/router_strategy/tag_based_routing.py:757
↓ 9 callers
Function
get_team_callbacks
Get the success/failure callbacks and variables for a team Parameters: - team_id (str, required): The unique identifier for the team
litellm/proxy/management_endpoints/team_callback_endpoints.py:762
↓ 9 callers
Method
get_unified_output_file_id
( self, output_file_id: str, model_id: str, model_name: str | None = None,
litellm/proxy/openai_files_endpoints/common_utils.py:119
↓ 9 callers
Method
get_vertex_ai_project
(litellm_params: dict)
litellm/llms/vertex_ai/vertex_llm_base.py:1194
↓ 9 callers
Function
get_vertex_regional_endpoint_uplift
Resolve the per-model uplift multiplier for Vertex AI non-global (regional and multi-region) endpoints. Google prices every non-global e
litellm/litellm_core_utils/llm_cost_calc/utils.py:1475
↓ 9 callers
Function
github_copilot_auth_mode
Whether this call runs in per-user mode. A resolved credential's stored ``credential_values`` are the only authority once a credential is named an
litellm/llms/github_copilot/per_user_auth.py:599
↓ 9 callers
Function
group_tool_exchanges
Group message indices into tool exchanges: an assistant row that made tool calls, together with the tool rows answering the ids it declared.
litellm/litellm_core_utils/prompt_templates/factory.py:2689
↓ 9 callers
Function
guardrails_usage_detail
Return single guardrail usage metrics and time series.
litellm/proxy/guardrails/usage_endpoints.py:634
↓ 9 callers
Function
hT
(e,t="Assertion error")
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 9 callers
Method
handle_logging_collected_chunks
1. Convert all_chunks to a ModelResponseStream 2. combine model_response_stream to model_response 3. Return the model_respons
litellm/llms/gigachat/passthrough/transformation.py:139
↓ 9 callers
Function
has_header
(headers: &[(String, String)], name: &str)
litellm-rust/crates/http/src/request.rs:84
↓ 9 callers
Function
has_non_string_content
Return True if any inspected content is not a plain string. Used by hooks whose mask/redact path operates on string offsets and therefore can
litellm/proxy/guardrails/_content_utils.py:531
↓ 9 callers
Function
headers
(pairs: impl IntoIterator<Item = (&'a str, &'a str)>)
litellm-rust/crates/inference-messages/tests/messages/main.rs:93
↓ 9 callers
Function
hop_reply
(response_id: str, hop: Hop, stream: bool, abort_after: int | None = None)
tests/integration/providers/_gemini_long_decode_support.py:117
↓ 9 callers
Function
i
(e,s)
litellm/proxy/_experimental/out/_next/static/chunks/2jxpy6eth1zvy.js:1
↓ 9 callers
Function
iQ
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 9 callers
Method
ids_for_agent
(self, agent_id: str)
litellm/proxy/agent_endpoints/agent_registry.py:458
↓ 9 callers
Function
independent_snapshot
A copy of ``data`` whose top-level keys are deep-copied independently where possible -- always attempted, regardless of ``litellm.safe_me
litellm/litellm_core_utils/core_helpers.py:837
↓ 9 callers
Function
infer_openai_data_residency
Derive the OpenAI data-residency region from an api_base URL. Returns ``"eu"`` for the EU regional host, ``"us"`` for the US regional ho
litellm/llms/openai/data_residency.py:27
↓ 9 callers
Function
invalid_value
(field: &'static str, expected: &'static str, actual: Value)
litellm-rust/crates/llms/src/anthropic/messages/handler.rs:228
↓ 9 callers
Function
invoke
()
tests/unit/mcp_client/test_mcp_client.py:3110
↓ 9 callers
Function
ip
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 9 callers
Function
ir_to_systemone_request
(model: str, request: DecisionsIRRequest)
litellm/llms/base_llm/decisions/transformation.py:301
↓ 9 callers
Method
isInSet
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 9 callers
Function
isJSONReferenceLikeElement
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 9 callers
Function
is_admin_view_safe
Safely determine if the current user has admin view permissions. Defaults to False on any exception.
litellm/proxy/spend_tracking/spend_management_endpoints.py:4753
↓ 9 callers
Function
is_background_response
Whether a retrieved object is a response created with ``background=true``. Such a create returns ``status="queued"`` and no usage at all, so noth
litellm/litellm_core_utils/internal_call_metadata.py:89
↓ 9 callers
Method
is_chunk_non_empty
( self, completion_obj: Mapping[str, object], model_response: ModelResponseStream,
litellm/litellm_core_utils/streaming_handler.py:1099
↓ 9 callers
Method
is_claimed
(self, interaction_id)
tests/unit/interactions/test_background_cost_polling.py:1171
↓ 9 callers
Method
is_database_infrastructure_error
True when the failure came from the database or its query engine rather than from the caller's request. This answers a reporting ques
litellm/proxy/db/exception_handler.py:166
↓ 9 callers
Method
is_empty
(&self)
litellm-rust/crates/db/src/spend/key_spend.rs:24
↓ 9 callers
Function
is_opaque
A value the host passed as an opaque token: the merge moves it, never reads it.
litellm-rust/crates/router-core/src/model_info.rs:24
↓ 9 callers
Method
is_partitioned
(self, prisma_client: "PrismaClient", remaining_timeout_ms: RemainingTimeoutMs)
litellm/proxy/db/db_transaction_queue/spend_logs_partition_manager.py:165
↓ 9 callers
Method
is_permanent_database_fault
True for a service-unavailable failure that will not clear on its own: an engine-layer ``PrismaError`` (missing or version-skewed engine
litellm/proxy/db/exception_handler.py:503
↓ 9 callers
Method
is_response_api_usage
returns True if usage is from OpenAI Response API
litellm/responses/utils.py:1280
↓ 9 callers
Function
is_snowflake_claude_model
Return True if model name (after stripping snowflake/ prefix) is a Claude model.
litellm/llms/snowflake/chat/transformation.py:101
↓ 9 callers
Function
is_system_message
(message: object)
litellm/litellm_core_utils/prompt_templates/mid_conversation_system.py:93
↓ 9 callers
Method
is_tool_allowed_for_server
Check if a specific tool is allowed for a server based on key/team permissions. Args: tool_name: Bare tool name, already
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:3476
↓ 9 callers
Method
is_tool_search_used
Check if tool search tools are present in the tools list.
litellm/llms/anthropic/common_utils.py:826
↓ 9 callers
Function
is_valid_sha256_hash
(value: str)
litellm/litellm_core_utils/litellm_logging.py:6889
↓ 9 callers
Function
iter_known_server_prefixes
Yield every prefix form that may appear in tool names for ``server``. Always includes the *current* prefix returned by ``get_server_prefix``.
litellm/proxy/mcp_server/utils.py:365
↓ 9 callers
Function
joined
(events: Sequence[Mapping[str, JsonValue]], kind: str, output_index: int, **match: JsonValue)
tests/integration/streaming/faked_responses_case.py:191
↓ 9 callers
Method
json
(self)
litellm/llms/vertex_ai/vector_stores/rag_api/transformation.py:80
↓ 9 callers
Method
json
(self)
litellm/integrations/galileo.py:61
↓ 9 callers
Method
json
(&self)
litellm-rust/crates/inference-messages/tests/support/mod.rs:93
↓ 9 callers
Method
json_body
(self)
tests/unit/llms/anthropic/test_anthropic_wif.py:79
↓ 9 callers
Function
json_response
(body: Mapping[str, object] | bytes, *, status: int = 200)
tests/rust-python-harness/strategies/trace_parity/fixtures.py:22
↓ 9 callers
Function
jsonify_object
(data: dict)
litellm/proxy/utils.py:5354
↓ 9 callers
Function
jwtKeyMappingTestServer
(t *testing.T, mapping JWTKeyMappingResponse)
terraform/provider/litellm/resource_jwt_key_mapping_crud_test.go:44
↓ 9 callers
Function
k
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 9 callers
Function
key_generation_check
Check if admin has restricted key creation to certain roles for teams or individuals
litellm/proxy/management_endpoints/key_management_endpoints.py:852
↓ 9 callers
Function
l
()
litellm/proxy/_experimental/out/_next/static/chunks/1k52o6u_65gki.js:2
↓ 9 callers
Function
labelWithHint
(label: React.ReactNode, hint: string)
ui/litellm-dashboard/src/app/(dashboard)/agents/_components/AgentFormKit.tsx:108
↓ 9 callers
Function
landed_once_undropped
(sents: tuple[Sent, ...])
tests/integration/providers/_idle_upstream_support.py:627
↓ 9 callers
Function
langfuse_preset
( *, config_overrides: OpenTelemetryV2Config | None = None, allow_missing_credentials: bool = Fals
litellm/integrations/otel/presets/langfuse.py:20
↓ 9 callers
Function
le
litellm/proxy/_experimental/out/_next/static/chunks/2k-fkubkt19cc.js:96
↓ 9 callers
Function
linux
()
litellm-rust/crates/testkit/tests/install.rs:15
↓ 9 callers
Function
listMCPTools
( accessToken: string, serverId: string, customHeaders?: Record<string, string>, includeDisabledTools?
ui/litellm-dashboard/src/components/networking.tsx:4821
↓ 9 callers
Function
list_keys
List all keys for a given user / team / organization. Parameters: expand: Optional[List[str]] - Expand related objects (e.g. 'user'
litellm/proxy/management_endpoints/key_management_endpoints.py:7241
↓ 9 callers
Function
list_tools_with_pagination
Collect tools from every tools/list page by following nextCursor. Stops and returns the tools collected so far when the upstream repeats a cu
litellm/mcp_client/tools.py:104
↓ 9 callers
Function
litellm_call_id_headers
(litellm_call_id: str | None)
litellm/proxy/common_utils/openai_error_payload.py:247
↓ 9 callers
Method
litellm_response
(self)
tests/integration/providers/test_decisions_openai_format_wire.py:147
↓ 9 callers
Function
live_model_ids_snapshot
The ids this pod's router is currently serving, read fresh from the module global because a reload can rebind it. The empirical ground truth every
litellm/proxy/management_endpoints/model_management_endpoints.py:3928
↓ 9 callers
Function
llm_passthrough_route
Pass through requests to the LLM APIs. Step 1. Build the request Step 2. Send the request Step 3. Return the response
litellm/passthrough/main.py:423
↓ 9 callers
Method
load
(self)
litellm/rust_bridge/bindings.py:29
↓ 9 callers
Method
load_all
Scan GitLab for all .prompt files under prompts_path, load and parse each, and return the mapping of repo file path -> JSON-like dict
litellm/integrations/gitlab/gitlab_prompt_manager.py:687
← previous
next →
8,101–8,200 of 202,479, ranked by callers