MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 30 callersMethodroute_for
Return the tracer (and trace-detachment flag) for this request. Use ``default`` unless the request's dynamic credentials, its key/team
litellm/integrations/otel/plumbing/routing.py:216
↓ 30 callersFunctionrunning_edge
(backend: EdgeBackend, mounts: Mapping[str, str])
tests/e2e_harness/test_provider_edge.py:312
↓ 30 callersMethodsend
(self, request: httpx.Request, *, stream: bool, follow_redirects: bool)
litellm/proxy/agent_endpoints/kill_switch.py:150
↓ 30 callersMethodset_arize_attributes
(span: Span, kwargs, response_obj)
litellm/integrations/arize/arize.py:173
↓ 30 callersFunctionset_io_token_rate_limit_request_kwargs
( kwargs: dict[str, object] | None, store_in_context: bool = True, *, opens_responses_socket:
litellm/router_utils/pre_call_checks/io_token_rate_limit_check.py:104
↓ 30 callersMethodsource
(&self)
litellm-rust/crates/auth-types/src/lib.rs:36
↓ 30 callersFunctiontime
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 30 callersFunctionto_value
(request: MessagesRequest)
litellm-rust/crates/llms/src/azure_ai/messages/transformation.rs:148
↓ 30 callersMethodtranslate_generate_content_to_completion
Transform generate_content request to litellm completion format Args: model: The model name contents: Genera
litellm/google_genai/adapters/transformation.py:456
↓ 30 callersFunctionuseTerminology
()
ui/litellm-dashboard/src/contexts/TerminologyContext.tsx:18
↓ 30 callersMethodvalues
(self, rig: FederationRig, tag: str)
tests/integration/management/test_credential_federation_values.py:913
↓ 29 callersFunction_catalog_manager
(*upstream_tools: MCPTool)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:20002
↓ 29 callersFunction_deployment
( scenario: Scenario, wire: Wire, backend: str, *, base: str = _OPENAI_BASE, api_key:
tests/integration/providers/test_bedrock_mantle_output_limit_wire.py:248
↓ 29 callersFunction_granted_key
(rig: Rig)
tests/integration/mcp/test_mcp_llm_endpoints.py:626
↓ 29 callersFunction_grayswan_config
( tmp_path: Path, identity: str, vendor_url: str, mode: str, *, on_flagged_action: str
tests/integration/observability/test_grayswan_wire.py:61
↓ 29 callersFunction_make_wrapper
(engine_pid: int = 111, iam: bool = False)
tests/unit/proxy/db/test_prisma_planned_engine_restart.py:59
↓ 29 callersFunction_payload
(response: httpx.Response)
tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py:303
↓ 29 callersFunction_plan
(query_params: Mapping[str, str], spec: ListSpec[BudgetRow, BudgetOut] | None = None)
tests/unit/proxy/list_api/test_list_framework.py:121
↓ 29 callersFunction_received
(wire: Wire, expected: int)
tests/integration/providers/test_bedrock_stream_timeout_wire.py:331
↓ 29 callersMethod_record
(self, name: str, kwargs: object = None, response: object = None)
tests/test_litellm_rust/support/callback_recorder.py:44
↓ 29 callersFunction_register
( proxy: ProxyClient, resources: ResourceManager, params: LiteLLMParamsBody, prefix: str = "e2e-responses"
tests/e2e/llm_translation/test_responses_e2e.py:139
↓ 29 callersFunction_rig
(gateway: Gateway, *filenames: str, listing: Callable[[str, str], Listing] | None = None)
tests/integration/management/test_vector_store_file_list_managed_ids.py:426
↓ 29 callersFunction_sample_agent_card_params
()
tests/unit/proxy/agent_endpoints/test_agent_registry.py:29
↓ 29 callersFunction_server
(mode: str = "enforce", **binding_overrides: object)
tests/unit/proxy/mcp_server/test_oauth_identity_binding.py:78
↓ 29 callersFunction_success_row
(request_id: str)
tests/integration/providers/test_bedrock_kimi_k3_cache_point_wire.py:545
↓ 29 callersFunction_team
(team_id: str, *members: str, org: str | None = None, alias: str | None = None)
tests/unit/proxy/management_helpers/test_bulk_user_deletion.py:231
↓ 29 callersFunction_throttle
A throttle over real in-memory stores, so the tests exercise the true counters and blocks.
tests/unit/proxy/auth/test_login_utils.py:657
↓ 29 callersFunction_write_legacy_file
(home, **overrides)
tests/unit/litellm_core_utils/test_cli_token_utils.py:63
↓ 29 callersFunctiona
()
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:1
↓ 29 callersMethodaclose
(self)
tests/unit/proxy/proxy_server/test_routes_audio.py:195
↓ 29 callersMethodapi_base
(self)
tests/integration/observability/test_prometheus_provider_auth_failure.py:366
↓ 29 callersMethodasync_increment_cache
Key - the key in cache Value - float - the value you want to increment by Refresh_ttl - bool - if True, resets the Redis TT
litellm/caching/dual_cache.py:541
↓ 29 callersFunctioncache_edge
A cache edge standing in for one pytest process. A fresh instance over the same store is the next build running the same test: the recordings surv
tests/code_coverage_tests/test_provider_cache.py:189
↓ 29 callersFunctionchat_backend
( identity: str, *, stream: bool, name: str = "Bash", arguments: Mapping[str, JsonValue] |
tests/integration/_support/safeguards_rig.py:495
↓ 29 callersMethodclose
(self)
tests/unit/proxy/guardrails/test_custom_code_security.py:433
↓ 29 callersFunctioncreate_responses_config_class
Generate a Responses API config class dynamically from JSON configuration. Parallel to create_config_class() but for /v1/responses endpoints.
litellm/llms/openai_like/dynamic_config.py:233
↓ 29 callersFunctiondecode
Decode *managed_id*. Returns ``None`` for anything that is not a passthrough managed ID — raw OpenAI IDs, unified-endpoint IDs, garbage,
litellm/proxy/pass_through_endpoints/managed_id_codec.py:48
↓ 29 callersMethodemit
(self, record: logging.LogRecord)
tests/unit/integrations/vector_store_integrations/test_vector_store_pre_call_hook.py:105
↓ 29 callersFunctionend_user_cache_key
Cache key one end-user row is stored under; shared so auth and spend tracking cannot drift.
litellm/proxy/common_utils/user_api_key_cache.py:555
↓ 29 callersMethodensure_oauth_metadata_discovered
( self, server: MCPServer, *, needed_endpoint: Callable[[MCPServer], str | Non
litellm/proxy/mcp_server/mcp_server_manager.py:2363
↓ 29 callersMethodeval
(self, script: str, numkeys: int, *keys_and_args: str | bytes | float)
litellm/caching/redis_cache.py:93
↓ 29 callersFunctionevict_and_broadcast
Drop cached management objects here and on every other worker. Every endpoint that mutates a cached object must call this: auth serves those
litellm/proxy/common_utils/auth_cache_invalidation_pubsub.py:220
↓ 29 callersMethodget_config_model
Returns the config model for the guardrail This is used to render the config model in the UI.
litellm/integrations/custom_guardrail.py:841
↓ 29 callersFunctionget_end_user_object
Returns end user object from database or cache. If end user exists but has no budget_id, applies the default budget: the key's ``end_use
litellm/proxy/auth/auth_checks.py:2206
↓ 29 callersMethodget_model_ids
( self, model_name: str | None = None, exclude_team_models: bool = False )
litellm/router_deprecated.py:497
↓ 29 callersFunctionget_or_create_metadata_bucket
Return the proxy-internal metadata bucket for this request, creating it if absent. Batch/file routes store proxy state in ``litellm_metadata
litellm/litellm_core_utils/core_helpers.py:509
↓ 29 callersFunctionget_prisma_client_or_throw
(message: str)
litellm/proxy/management_endpoints/mcp_management_endpoints.py:1077
↓ 29 callersFunctionhandle_realtime_stream_cost_calculation
Handles the cost calculation for realtime stream responses. Pick the 'response.done' events. Calculate total cost across all 'response.done'
litellm/cost_calculator.py:3864
↓ 29 callersMethodhealth_check_server
Perform a health check on a specific MCP server. Args: server_id: The ID of the server to health check mcp_a
litellm/proxy/mcp_server/mcp_server_manager.py:7598
↓ 29 callersMethodinsert
(&mut self, key: String, time: Duration)
litellm-rust/crates/redis-store/src/dual_cache/batch_read.rs:226
↓ 29 callersMethodinvoke
(self, op: Literal["acompletion"])
litellm/router_python_host.py:66
↓ 29 callersMethodis_key_within_model_budget
(self, user_api_key_dict: UserAPIKeyAuth, model: str)
litellm/proxy/auth/user_api_key_auth.py:416
↓ 29 callersFunctionjson_response
(body: Mapping[str, JsonValue], status: int = 200)
tests/integration/caching/response_cache_case.py:239
↓ 29 callersMethodkeys
(self)
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_safeguards_beta_wire.py:78
↓ 29 callersMethodlines
(self)
tests/unit/proxy/batches_endpoints/test_litellm_executed_batches.py:301
↓ 29 callersMethodmap_openai_params
( self, non_default_params: dict, optional_params: dict, model: str, d
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:1839
↓ 29 callersMethodmodel_dump
(self, *, exclude_none: bool = ...)
litellm/responses/streaming_iterator.py:1592
↓ 29 callersFunctionnew_marker
()
tests/integration/routing/_prompt_cache_pin_support.py:50
↓ 29 callersMethodpost_call
(error: Self)
litellm-rust/crates/inference/src/error.rs:46
↓ 29 callersFunctionpost_chat
(gateway: Gateway, body: dict[str, JsonValue], *, key: str | None = None)
tests/integration/providers/_cache_control_marks_support.py:443
↓ 29 callersFunctionprometheus_label_factory
Returns a dictionary of label + values for prometheus. Ensures end_user param is not sent to prometheus if it is not supported. When ``
litellm/integrations/prometheus.py:5066
↓ 29 callersFunctionprovider_url
(server: ThreadingHTTPServer)
tests/e2e_harness/test_provider_edge.py:142
↓ 29 callersMethodpush
(e)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 29 callersMethodr
litellm/proxy/_experimental/out/_next/static/chunks/1gr6rzkj48efi.js:1
↓ 29 callersMethodread
(self, counter: str)
tests/unit/redis/stores/spend_counters_double.py:103
↓ 29 callersMethodrecord_failure
(self, exception, traceback_exception, **kwargs)
tests/unit/responses/test_responses_websocket_all_providers.py:4749
↓ 29 callersFunctionrefetch
(token: str)
tests/unit/mcp_client/test_mcp_client.py:5214
↓ 29 callersMethodregister_agent
(self, agent_config: AgentResponse)
litellm/proxy/agent_endpoints/agent_registry.py:433
↓ 29 callersMethodregister_tool
(self, name, description, input_schema, handler)
tests/unit/proxy/mcp_server/test_rest_endpoints.py:4292
↓ 29 callersMethodreplace
Every deployment at once (``router.model_list = [...]``).
litellm/router_rust/surface/model_list.py:331
↓ 29 callersFunctionrequest_body
( endpoint: Endpoint, model: str, prompt: str, *, stream: bool = False, **extra: JsonValue )
tests/integration/providers/_mantle_gpt_prompt_cache_support.py:412
↓ 29 callersFunctionresponses_peer
(cert: tuple[Path, Path], script: Script = seven)
tests/integration/_support/responses_ws_peer.py:115
↓ 29 callersMethodroute_image_generation_cost_calculator
Route the image generation cost calculator based on the custom_llm_provider ``model_info`` is the deployment's own price table. Its
litellm/litellm_core_utils/llm_cost_calc/utils.py:2287
↓ 29 callersFunctionserver_span_factory
Factory mirroring user_api_key_auth: SERVER span + url.path + http.route.
tests/unit/integrations/open_telemetry/conftest.py:47
↓ 29 callersMethodshould_call_route
Check if management route is disabled and raise exception
litellm/proxy/auth/route_checks.py:125
↓ 29 callersFunctionspend_log_error
Log a spend-tracking error, with the traceback gated on the env var. By default this behaves like ``verbose_proxy_logger.exception`` — the ac
litellm/proxy/spend_tracking/spend_log_error_logger.py:59
↓ 29 callersMethodstore_batch_output_file
Register file metadata, optionally fetching provider details.
litellm/proxy/openai_files_endpoints/common_utils.py:126
↓ 29 callersMethodstream
(self, model: str, behavior: Behavior, marker: str, **extra: JsonValue)
tests/integration/routing/test_messages_stream_retry_budget_sources_owned_proxy.py:180
↓ 29 callersMethodtransform_openai_jsonl_content_to_bedrock_jsonl_content
( self, openai_jsonl_content: Sequence[_OpenAIBatchRecord], target_model: str = "",
litellm/llms/bedrock/files/transformation.py:1250
↓ 29 callersMethodupdate_config_state
(self, config: Mapping[str, object])
litellm/proxy/proxy_server.py:6637
↓ 29 callersFunctionw
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 29 callersFunctionwindow_end
(window_seconds: int, room_seconds: int)
tests/integration/management/_batch_file_caps.py:232
↓ 28 callersFunctionF
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/37cr8te-omsl0.js:1
↓ 28 callersFunctionMn
(t,e,r,n)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 28 callersFunction_admin
()
tests/unit/proxy/management_endpoints/test_access_group_management.py:855
↓ 28 callersFunction_assert_completed
(answer: _Answer, *, stream: bool = False)
tests/integration/providers/test_responses_bridge_message_cache_control_wire.py:142
↓ 28 callersFunction_auth
( user_id: str = "owner-user", team_id: str = "owner-team", user_role: LitellmUserRoles | None = None )
tests/unit/test_responses_id_security.py:783
↓ 28 callersFunction_aws_event_frame
( event_type: str, payload: Mapping[str, JsonValue], scenario_id: str, unique_id: str, )
tests/integration/_support/upstream.py:155
↓ 28 callersFunction_chat_body
(model: str, marker: str, *, stream: bool = False)
tests/integration/routing/test_non_chat_model_endpoint_gate.py:242
↓ 28 callersFunction_converse
(scenario: Scenario, wire: Wire, **extra: JsonValue)
tests/integration/providers/test_bedrock_stream_timeout_wire.py:169
↓ 28 callersFunction_converse_deployment
(scenario: Scenario, wire: Wire, **extra: JsonValue)
tests/integration/providers/test_bedrock_converse_missing_content_wire.py:188
↓ 28 callersFunction_failures
( head: object, changed_files: tuple[str, ...] = MAP_FILES, bot: bool = True, evaluation_outpu
tests/unit/test_cost_map_guard.py:67
↓ 28 callersFunction_ids
(page: Mapping[str, JsonValue])
tests/integration/management/test_vector_store_file_list_managed_ids.py:308
↓ 28 callersFunction_leg_record
Spec'd like a real prisma row: only the table's columns exist as attributes. One row is one key's leg of a job; legs sharing group_id are one job.
tests/unit/proxy/management_endpoints/test_auto_router_endpoints.py:1498
↓ 28 callersFunction_make_handler
Construct the handler with auth + proxy seams patched at the instance level. ``_ensure_access_token`` and ``_check_custom_proxy`` are inherited f
tests/unit/llms/vertex_ai/batches/test_handler.py:83
↓ 28 callersFunction_mantle_peer
(prompt: str, reply: Reply)
tests/integration/providers/test_bedrock_mantle_context_overflow_wire.py:146
↓ 28 callersFunction_policy_call_id_matches
(payload: Mapping[str, JsonValue], call_id: str)
tests/integration/observability/_logging_only_scope_support.py:974
↓ 28 callersFunction_proxy_health_globals
( llm_model_list: Sequence[Mapping[str, object]], llm_router: object, use_background_health_checks
tests/unit/proxy/health_endpoints/test_health_endpoints.py:2475
↓ 28 callersFunction_reset_upstream
(upstream_url: str)
tests/integration/observability/_logging_only_scope_support.py:920
↓ 28 callersFunction_resolve_user_provider_credentials_for_request
Resolve the calling user's per-user provider connections into secret_fields. Runs after model alias rewrites so ``data['model']`` is the final re
litellm/proxy/litellm_pre_call_utils.py:3471
← previousnext →1,701–1,800 of 202,479, ranked by callers