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
↓ 26 callers
Method
add
(self, report: LocationReport)
litellm/proxy/management_endpoints/credential_migration.py:111
↓ 26 callers
Method
add
(self, other: Self)
litellm-rust/crates/redis-store/src/number.rs:77
↓ 26 callers
Function
app
(model: &str, api_base: &str)
litellm-rust/crates/gateway-inference/tests/support/mod.rs:34
↓ 26 callers
Function
as_router
A ``litellm.Router`` facade over ``core``, as ``Router.from_config`` attaches the core it builds.
tests/unit/test_router/core/test_deprecated_members.py:28
↓ 26 callers
Method
as_str
(self)
litellm-rust/crates/inference-messages/src/common_utils.rs:31
↓ 26 callers
Method
async_live_session
(self, **kwargs: object)
tests/unit/realtime_api/test_main.py:280
↓ 26 callers
Method
async_log_failure_event
( self, kwargs: Mapping[str, object], response_obj: object | None, start_time:
tests/unit/integrations/clickhouse/test_clickhouse_spend_logger.py:65
↓ 26 callers
Method
async_moderation_hook
(self, data, user_api_key_dict, call_type)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:17811
↓ 26 callers
Method
async_post_call_failure_hook
( self, request_data: dict[str, object], original_exception: Exception, user_a
tests/unit/proxy/mcp_server/test_mcp_logging.py:66
↓ 26 callers
Function
at
(value: JsonValue, *keys: str | int)
tests/integration/providers/_gemini_long_decode_support.py:281
↓ 26 callers
Function
call
(server: RecordingServer, *, asynchronous: bool = True, **kwargs: object)
tests/test_litellm_rust/responses/data.py:60
↓ 26 callers
Function
call_ocr
(server: RecordingServer, **kwargs: object)
tests/test_litellm_rust/ocr/data.py:27
↓ 26 callers
Function
chat_body
(model: str, messages: Sequence[JsonValue], **fields: JsonValue)
tests/integration/providers/_cache_control_marks_support.py:125
↓ 26 callers
Function
check_batch_file_upload
( filename: str | None, file_source: bytes | BinaryIO, max_batch_file_size_mb: int | None, lin
litellm/proxy/openai_files_endpoints/batch_file_validation.py:144
↓ 26 callers
Function
collect_model_deprecations
Bucket every deployment carrying a deprecation date by how urgent it is
litellm/proxy/common_utils/model_deprecation.py:326
↓ 26 callers
Function
completed
(received: tuple[dict[str, JsonValue], ...])
tests/integration/_support/responses_ws_peer.py:180
↓ 26 callers
Method
connect
(self)
tests/unit/proxy/management_endpoints/test_key_generate_prisma.py:2261
↓ 26 callers
Function
credential_store
Stands the credential store up for one test: whether the database is reachable, what the proxy is already serving from memory, which router deploy
tests/unit/proxy/credential_endpoints/test_endpoints.py:90
↓ 26 callers
Function
deployment
(scenario: Scenario, provider: Provider, wire_url: str, upstream_url: str)
tests/integration/providers/_tool_search_support.py:166
↓ 26 callers
Function
e
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 26 callers
Function
enforce_oauth_identity_binding
Validate the exchanged token's upstream principal against the LiteLLM caller. No-op when the server has no binding or it is disabled. In enforce
litellm/proxy/mcp_server/oauth_identity_binding.py:371
↓ 26 callers
Method
expand_permission_list
Expand a permission list of server_ids/names/aliases into concrete server_ids against the current region's config + DB registry union
litellm/proxy/mcp_server/mcp_server_manager.py:7430
↓ 26 callers
Function
extract_file_parts_from_messages
( structured_messages: Sequence[object] | None, size_limit: int | None = None )
litellm/proxy/guardrails/guardrail_hooks/ovalix/ovalix_extraction.py:190
↓ 26 callers
Method
flush_and_get_aggregated_db_spend_update_transactions
Flush all updates from the queue and return all updates aggregated by entity type.
litellm/proxy/db/db_transaction_queue/spend_update_queue.py:27
↓ 26 callers
Function
general_settings_view
()
litellm/proxy/proxy_server.py:3163
↓ 26 callers
Method
get_available_deployment
(self, *args: object, **kwargs: object)
tests/unit/router_utils/test_kubernetes_pod_discovery.py:74
↓ 26 callers
Method
get_chat_completion_prompt
( self, model: str, messages: List[AllMessageValues], non_default_params: dict
tests/unit/integrations/test_custom_prompt_management.py:24
↓ 26 callers
Function
get_litellm_metadata_from_kwargs
Helper to get litellm metadata from all litellm request kwargs Return `litellm_metadata` if it exists, otherwise return `metadata`
litellm/litellm_core_utils/core_helpers.py:583
↓ 26 callers
Method
get_openai_compatible_provider_info
( self, api_base: str | None, api_key: str | None, )
litellm/llms/v0/chat/transformation.py:31
↓ 26 callers
Function
get_projected_spend_over_limit
( current_spend: float, soft_budget_limit: float | None, budget_duration: str | None = None, b
litellm/proxy/utils.py:9571
↓ 26 callers
Function
get_team_access
()
litellm/proxy/management/teams/dependencies.py:7
↓ 26 callers
Function
get_tool_calls_from_response
Extract tool/function calls from a response object into a normalized ``{"id", "name", "arguments"}`` shape, regardless of which API surface
litellm/litellm_core_utils/prompt_templates/factory.py:6516
↓ 26 callers
Function
identity
(cell: str)
tests/integration/observability/test_prometheus_provider_auth_failure.py:108
↓ 26 callers
Method
is_ok
(self)
litellm/proxy/mcp_server/outbound_credentials/result.py:36
↓ 26 callers
Method
json
(self)
litellm/llms/gemini/agents/transformation.py:32
↓ 26 callers
Function
langfuse_rig
( gateway: Gateway, tmp_path: Path, settings: Mapping[str, object], marker: str, *, si
tests/integration/observability/_langfuse_otel_metadata_support.py:204
↓ 26 callers
Method
list
(self, call: ListCall, key: str | None = None)
tests/integration/security/test_managed_file_listing.py:162
↓ 26 callers
Function
litellm_params
(metadata_key, **metadata)
tests/unit/llms/bedrock/test_request_metadata.py:39
↓ 26 callers
Function
mint_session_token
Mint the short-lived session ACCESS token for ``principal``. ``exp`` is ``SESSION_TTL_SECONDS`` from ``now``. Returns ``SessionTokenTooLarge`` wh
litellm/proxy/mcp_server/outbound_credentials/session_token.py:336
↓ 26 callers
Method
model_dump
(self)
litellm/proxy/management_endpoints/key_management_endpoints.py:235
↓ 26 callers
Method
model_dump
(self, mode="json", exclude_none=False)
tests/unit/proxy/agent_endpoints/test_agent_headers.py:90
↓ 26 callers
Function
n
(...e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 26 callers
Method
oauth_discovery_slot
(self, server_id: str)
litellm/proxy/mcp_server/mcp_server_manager.py:2100
↓ 26 callers
Method
parse
()
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:2
↓ 26 callers
Function
place_mid_conversation_system
Apply the placement policy to the messages after the leading system run.
litellm/litellm_core_utils/prompt_templates/mid_conversation_system.py:536
↓ 26 callers
Function
process_response_headers
`preserve_litellm_internal_headers` must only be True when the input is a LiteLLM-owned dict (e.g. `_hidden_params["additional_headers"]` tha
litellm/litellm_core_utils/core_helpers.py:700
↓ 26 callers
Function
process_spend_logs_guardrail_usage
After spend logs are written: update DailyGuardrailMetrics and insert SpendLogGuardrailIndex rows from guardrail_information in each payload.
litellm/proxy/guardrails/usage_tracking.py:357
↓ 26 callers
Method
reap
Close every queued client that is due, idle, and closable from here. Called from the cache's read path, so the empty-queue exit comes first a
litellm/caching/evicted_client_closer.py:253
↓ 26 callers
Method
refresh
(self, user_id: str, server_id: str, token: OAuthToken)
tests/unit/proxy/mcp_server/outbound_credentials/test_oauth_token_store.py:207
↓ 26 callers
Function
response
(cost: float = 0.5)
tests/unit/proxy/spend_tracking/test_cost_finalization.py:78
↓ 26 callers
Method
rows
(self, query: str, parameters: tuple[str, ...])
tests/integration/_support/client.py:103
↓ 26 callers
Function
safe_set_attribute
Sets a span attribute safely with OTEL-compliant primitive typing for Arize/Phoenix.
litellm/integrations/opentelemetry_utils/base_otel_llm_obs_attributes.py:33
↓ 26 callers
Method
set
Replace the buffer's contents with a single fragment.
litellm/litellm_core_utils/json_fragment_accumulator.py:89
↓ 26 callers
Method
set_find_many_results
(self, results: List[Any])
tests/unit/proxy/common_utils/test_reset_budget_job.py:46
↓ 26 callers
Method
set_local
(self, key: str, value: object, ttl_seconds: float | None = None)
tests/unit/proxy/common_utils/test_user_api_key_cache.py:213
↓ 26 callers
Method
settings
(self)
litellm/proxy/telemetry/store.py:95
↓ 26 callers
Function
setup_cache
()
tests/unit/caching/test_caching_handler.py:64
↓ 26 callers
Method
store
(self)
tests/unit/redis/stores/fake_rate_limits.py:112
↓ 26 callers
Function
text_result
(text: str)
tests/integration/_support/mcp.py:381
↓ 26 callers
Function
tool_names
(gateway: Gateway, key: str, identity: str)
tests/integration/_support/mcp.py:572
↓ 26 callers
Method
transform_anthropic_messages_request
No transformation is needed for Anthropic messages This takes in a request in the Anthropic /v1/messages API spec -> transforms it
litellm/llms/anthropic/messages/native/transformation.py:670
↓ 26 callers
Method
transform_realtime_request
( self, message: str, model: str, session_configuration_request: str | None = None )
tests/unit/litellm_core_utils/test_realtime_streaming.py:1236
↓ 26 callers
Method
transform_realtime_response
Keep this state less - leave the state management (e.g. tracking current_output_item_id, current_response_id, current_conversation_id, curren
litellm/llms/gemini/realtime/transformation.py:1451
↓ 26 callers
Method
unobserve
()
ui/litellm-dashboard/tests/setupTests.ts:229
↓ 26 callers
Method
update
(self, where: Mapping[str, object], data: Mapping[str, object])
tests/unit/proxy/policy_engine/test_policy_registry.py:75
↓ 26 callers
Method
update_variables
(self, llm_router: Router)
litellm/proxy/hooks/dynamic_rate_limiter.py:86
↓ 26 callers
Function
x
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 25 callers
Function
K
()
litellm/proxy/_experimental/out/_next/static/chunks/1a2lzi3ursud4.js:1
↓ 25 callers
Method
_addCheck
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 25 callers
Method
_auth_with_aws_role
Authenticate with AWS Role
litellm/llms/bedrock/base_aws_llm.py:1239
↓ 25 callers
Function
_blob
(base_url=SERVER, key="sk-vault", jwt_token="", timestamp=0.0, refresh_token=None)
tests/unit/litellm_core_utils/test_cli_token_utils.py:89
↓ 25 callers
Function
_build
(payload: dict | None = None, metadata: dict | None = None)
tests/unit/proxy/db/test_autorouter_session_rollup.py:57
↓ 25 callers
Function
_cache_with_project
( project_id: str, project_models: list[str], team_id: str | None = "team-lit-5823", project_max_budge
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:21055
↓ 25 callers
Function
_call
()
tests/integration/routing/test_vllm_passthrough_stream_relay.py:53
↓ 25 callers
Method
_call_panw_api
Call PANW Prisma AIRS API to scan content or a tool_event.
litellm/proxy/guardrails/guardrail_hooks/panw_prisma_airs/panw_prisma_airs.py:390
↓ 25 callers
Function
_chunk
()
tests/unit/proxy/policy_engine/test_pipeline_executor.py:1245
↓ 25 callers
Function
_collect_events
( iterator: LiteLLMCompletionStreamingIterator, sync_mode: bool )
tests/unit/responses/litellm_completion_transformation/test_streaming_iterator_transformation.py:1401
↓ 25 callers
Function
_config_handler
A real handler seeded with config-sourced YAML guardrails (no callbacks).
tests/unit/proxy/guardrails/test_usage_endpoints.py:36
↓ 25 callers
Function
_deployment
(scenario: Scenario, provider: Provider, wire_url: str, upstream_url: str)
tests/integration/providers/test_responses_bridge_tool_search_wire.py:553
↓ 25 callers
Function
_execute_virtual_key_regeneration
Generate new token, update DB, invalidate cache, and return response.
litellm/proxy/management_endpoints/key_management_endpoints.py:6261
↓ 25 callers
Function
_get_tools_from_mcp_servers
Helper method to fetch tools from MCP servers based on server filtering criteria. Args: user_api_key_auth: User authentication info
litellm/proxy/mcp_server/operations.py:1239
↓ 25 callers
Function
_hash_cli_sso_secret
(secret: str)
litellm/proxy/management_endpoints/ui_sso.py:307
↓ 25 callers
Method
_load_yaml_settings_stores
(self, config: Mapping[str, object])
litellm/proxy/proxy_server.py:5983
↓ 25 callers
Function
_logger
(upload_client: FakeUploadClient, **params)
tests/unit/integrations/pointfive/test_logger.py:44
↓ 25 callers
Function
_logging_obj
(call_id: str)
tests/unit/proxy/guardrails/guardrail_hooks/test_compresr.py:182
↓ 25 callers
Function
_make_iterator
( *, sse_events: list[bytes], logging_obj: LiteLLMLoggingObj, trailing_error: Optional[Excepti
tests/unit/responses/test_streaming_iterator.py:81
↓ 25 callers
Function
_make_logging_obj
()
tests/unit/interactions/test_agents_http_handler.py:65
↓ 25 callers
Function
_make_managed_file_row
( unified_file_id: str, purpose: str = "batch_output", created_by: str = "test-user", team_id:
tests/unit/enterprise/proxy/test_managed_files_hook.py:105
↓ 25 callers
Function
_make_managed_files_over_rows
(rows)
tests/unit/enterprise/proxy/test_managed_files_hook.py:179
↓ 25 callers
Function
_make_regenerate_mock_prisma
Mock prisma client shaped for _execute_virtual_key_regeneration.
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:13346
↓ 25 callers
Function
_marked_responses_input
()
tests/unit/router_utils/pre_call_checks/test_prompt_caching_deployment_check.py:1614
↓ 25 callers
Function
_marker
()
tests/integration/providers/test_bedrock_native_structured_output_wire.py:160
↓ 25 callers
Function
_mcp_request_ctx
()
tests/unit/proxy/mcp_server/conftest.py:127
↓ 25 callers
Function
_pkce_record
(**overrides)
tests/unit/proxy/client/cli/test_auth_commands.py:1688
↓ 25 callers
Function
_prisma_with_models
(rows, existing_sentinel_rows=())
tests/unit/proxy/spend_tracking/test_ptu_flat_cost_rollup.py:217
↓ 25 callers
Function
_routes
(served: tuple[Request, ...])
tests/integration/compatibility/test_openai_sdk_client_paths.py:130
↓ 25 callers
Function
_sent_types
(observed: tuple[dict[str, JsonValue], ...])
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:755
↓ 25 callers
Function
_state
(rig: Rig, interaction_id: str, state: InteractionState)
tests/integration/spend/test_background_interaction_settlement.py:274
↓ 25 callers
Function
_success_row
(model="gpt-4o", usage=None, **body_extra)
tests/unit/batches/test_batch_utils.py:54
↓ 25 callers
Method
_try_transform_vertex_batch_output_to_openai
Try to transform Vertex AI batch output to OpenAI format. If conversion fails at any point, return the original content as-is.
litellm/llms/vertex_ai/files/transformation.py:1642
← previous
next →
2,001–2,100 of 202,479, ranked by callers