MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 10 callersFunction_cache
( budgeted_groups: tuple[str, ...] = BUDGETED_GROUPS, member_allowed_models: tuple[str, ...] = (),
tests/unit/proxy/auth/test_model_access_group_budgets.py:70
↓ 10 callersFunction_caching_usage
(read: int, written: int, text: int = 10, out: int = 100)
tests/unit/proxy/spend_tracking/test_savings.py:203
↓ 10 callersFunction_call
(gateway: Gateway, route: str, key: str)
tests/integration/authorization/test_passthrough_route_denylist.py:33
↓ 10 callersFunction_call
(model_info: dict, response_cost: float, cache_hit: bool | None = None)
tests/unit/proxy/hooks/test_search_free_tier.py:51
↓ 10 callersFunction_call_as_admin
(data)
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:15604
↓ 10 callersFunction_call_id
(headers: httpx.Headers)
tests/integration/providers/_idle_upstream_support.py:164
↓ 10 callersFunction_caller
( virtual_key: bool = True, key_tools: list[str] | None | str = _NO_ROW, team_id: str | None = Non
tests/unit/proxy/auth/test_search_tool_deny_by_default.py:49
↓ 10 callersFunction_capability_reply
( *, p_solve: float, primary_rule: str = "SUP-1", capability_boundary: str = "supported",
tests/unit/router_strategy/test_complexity_router.py:2784
↓ 10 callersFunction_case
(identifier: str)
tests/rust-python-harness/shared/parity/fixtures/test_recording.py:248
↓ 10 callersFunction_chat
(gateway: Gateway, model: str, key: str, text: str)
tests/integration/spend/test_team_member_spend.py:168
↓ 10 callersFunction_chat
(gateway: Gateway, extra_body: Mapping[str, JsonValue] | None = None)
tests/integration/routing/test_model_capability_flags.py:211
↓ 10 callersMethod_chat
(self, params: dict[str, object], messages: List[AllMessageValues])
tests/unit/integrations/test_anthropic_cache_control_hook.py:3198
↓ 10 callersFunction_chat_completion_response
(model: str)
tests/unit/proxy/test_route_llm_request.py:1081
↓ 10 callersFunction_chat_stream
( rig: Rig, key: str, model: str, text: str, client: Client = "httpx", *, cached: bool = False )
tests/integration/providers/test_anthropic_refusal_stop_details_wire.py:310
↓ 10 callersFunction_chat_tool_call
(identity: str, city: str = "Paris")
tests/integration/observability/_openinference_support.py:867
↓ 10 callersFunction_check_custom_key_allowed
Raise 403 if custom API keys are disabled and a custom key was provided.
litellm/proxy/management_endpoints/key_management_endpoints.py:578
↓ 10 callersFunction_check_org_key_limits
Check if the organization key is allocating guaranteed throughput limits. If so, raise an error if we're overallocating. Only runs check if
litellm/proxy/management_endpoints/key_management_endpoints.py:2304
↓ 10 callersFunction_check_route_with_registered_routes
( route: str, valid_token: UserAPIKeyAuth, user_role: LitellmUserRoles = LitellmUserRoles.INTERNAL_USER )
tests/unit/proxy/auth/test_route_checks.py:4638
↓ 10 callersMethod_check_tool_permission
Check if a tool is allowed based on the configured rules Args: tool_name: Name of the tool to check tool_typ
litellm/proxy/guardrails/guardrail_hooks/tool_permission.py:673
↓ 10 callersFunction_check_user_permission_for_project
Check if user has permission to manage a project. Returns True if user is proxy admin, or a team admin of ``team_id`` when the ``team_ad
enterprise/litellm_enterprise/proxy/management_endpoints/project_endpoints.py:119
↓ 10 callersMethod_chunk
(content, finish_reason=None, index=0)
tests/unit/llms/openai/chat/guardrail_translation/test_openai_guardrail_handler.py:2619
↓ 10 callersFunction_chunks
(*chunks: bytes)
tests/unit/llms/bedrock/passthrough/guardrail_translation/test_handler.py:2552
↓ 10 callersFunction_claims
(**overrides: object)
tests/unit/proxy/mcp_server/test_id_jag_grant.py:68
↓ 10 callersMethod_cleanup_engine_watcher
Clean up pidfd reader, waitpid thread ref, or stop polling and reset state.
litellm/proxy/utils.py:7419
↓ 10 callersFunction_client_headers
(authorization_header_name: str | None = "authorization")
tests/unit/proxy/test_litellm_pre_call_utils.py:8731
↓ 10 callersFunction_closed_port
A port with nothing listening, so Redis calls fail fast and deterministically.
tests/unit/caching/test_redis_cache.py:431
↓ 10 callersFunction_collect
(iterator, stream)
tests/unit/llms/anthropic/messages/native/test_streaming_iterator.py:84
↓ 10 callersMethod_collect_streamed_text
( cls, guardrail: ContentFilterGuardrail, chunks: list[str], metadata: dict[st
tests/unit/proxy/guardrails/guardrail_hooks/content_filter/test_content_filter.py:1005
↓ 10 callersFunction_complete_cli_sso_callback_session
( *, request: Request, key: str, flow: dict, result: OpenID | dict, parsed_openid_resu
litellm/proxy/management_endpoints/ui_sso.py:2561
↓ 10 callersFunction_complete_flow
(cache: DualCache, device_code: str, session_data: Mapping[str, object] = _COMPLETED_SESSION)
tests/unit/proxy/anthropic_endpoints/test_gateway_endpoints.py:303
↓ 10 callersFunction_completed_text
(events: tuple[dict[str, JsonValue], ...])
tests/integration/providers/test_responses_websocket_session_limit.py:569
↓ 10 callersFunction_configured
(rate: int = 24_000, turn_detection: object = "server_vad", **kwargs: object)
tests/unit/llms/meta/realtime/test_meta_realtime_transformation.py:58
↓ 10 callersFunction_configured_deployment_router
(fetched: ResponsesAPIResponse)
tests/unit/proxy/response_api_endpoints/test_endpoints.py:1082
↓ 10 callersMethod_convert_mcp_to_llm_format
Convert MCP tool call to LLM message format for existing guardrail validation.
litellm/proxy/utils.py:2257
↓ 10 callersFunction_convert_single_content
Convert a single MCP content item to OpenAI format. For text/image/audio content, returns a single content-part dict. For tool_use/tool_resul
litellm/proxy/mcp_server/sampling_handler.py:315
↓ 10 callersFunction_cost_breakdown
(row: dict[str, JsonValue])
tests/integration/spend/test_service_tier_stream_billing.py:151
↓ 10 callersMethod_count_cache_control_blocks
(message: object, answered_tool_ids: Container[str] = frozenset())
litellm/integrations/anthropic_cache_control_hook.py:1181
↓ 10 callersFunction_count_user_content
(content: list[dict], model: str = "anthropic/claude-fable-5")
tests/unit/litellm_core_utils/test_token_counter.py:2572
↓ 10 callersFunction_create_context
(logging_obj: "LiteLLMLoggingObj", custom_llm_provider: str)
litellm/interactions/background_cost_polling.py:347
↓ 10 callersFunction_create_server
(client: ManagementClient, resources: ResourceManager)
tests/e2e/management/test_mcp_lifecycle_e2e.py:43
↓ 10 callersFunction_cyberark
(monkeypatch: pytest.MonkeyPatch, address: str)
tests/unit/rust_bridge/host/test_secret_manager.py:531
↓ 10 callersFunction_db_call_types
(hook: AsyncMock)
tests/unit/proxy/db/test_log_db_metrics.py:41
↓ 10 callersFunction_deferred_tools
()
tests/integration/providers/test_openai_responses_tool_search_wire.py:90
↓ 10 callersFunction_delete
(gateway: Gateway, team_ids: JsonValue, *, key: str | None = None)
tests/integration/management/test_team_delete_inputs.py:128
↓ 10 callersFunction_deployment
(scenario: Scenario, api_base: str)
tests/integration/providers/test_openai_count_tokens_tools_wire.py:29
↓ 10 callersFunction_deployment
(scenario: Scenario, wire: Wire, scenario_path: str, model: str)
tests/integration/providers/test_realtime_webrtc_http.py:89
↓ 10 callersFunction_deployment
( gateway: Gateway, scenario: Scenario, wire: Wire, model: str, model_info: Mapping[str, J
tests/integration/providers/test_bedrock_kimi_k3_cache_point_wire.py:1120
↓ 10 callersFunction_deployment
( gateway: Gateway, scenario: Scenario, wire: Wire, *, location: Mapping[str, JsonValue],
tests/integration/spend/test_vertex_image_regional_uplift.py:95
↓ 10 callersFunction_deployment
(scenario: Scenario, wire: Wire, form: str, bare: str)
tests/integration/routing/test_declared_provider_bare_model_routes.py:69
↓ 10 callersFunction_deployment
( limit: int | None, extra_body: dict[str, object] | None = None, deployment_id: str = "embed-depl
tests/unit/router_utils/test_embedding_batch_size_check.py:44
↓ 10 callersFunction_deployment
(model: str, dep_id: str)
tests/unit/router_utils/pre_call_checks/test_continuation_prefill_check.py:47
↓ 10 callersMethod_direct
(self, op: str, kwargs: Mapping[str, object])
litellm/router_rust/invoke/endpoints.py:1529
↓ 10 callersFunction_discoverable_models
(monkeypatch: pytest.MonkeyPatch, models: Mapping[str, list[str]])
tests/unit/proxy/proxy_server/test_routes_model_info.py:588
↓ 10 callersFunction_drain
(generator)
tests/unit/proxy/guardrails/guardrail_hooks/test_llm_shield_proxy.py:72
↓ 10 callersFunction_drain_async
(events: list)
tests/unit/llms/anthropic/messages/responses_adapters/test_responses_adapters_streaming_iterator.py:40
↓ 10 callersFunction_drained_other_than_model_list_probes
(wire: Wire)
tests/integration/security/test_files_batches_access.py:114
↓ 10 callersMethod_drive_with_canary
(self, extra_metadata=None, hidden_params=None, guardrail_information=None)
tests/unit/integrations/test_langfuse.py:648
↓ 10 callersFunction_ema_id_token
(sub: str = "u1")
tests/unit/proxy/management_endpoints/test_ui_sso.py:9609
↓ 10 callersFunction_embedding_router
( *, provider_model: str, api_base: str, max_embedding_batch_size: int | None, deployment_
tests/unit/router_utils/test_embedding_batch_size_check.py:83
↓ 10 callersFunction_encode_rsa_jwt
( private_key, issuer: str, audience: str, kid: str, extra_claims: Optional[dict] = None,
tests/unit/proxy/auth/test_jwt.py:1579
↓ 10 callersFunction_encoder
(router: RecordingRouter, **kwargs: Any)
tests/unit/router_strategy/test_litellm_encoder.py:41
↓ 10 callersMethod_encryption_boundary_key
The upstream encryption boundary a deployment's encrypted reasoning belongs to. The values are resolved the way the request resolves
litellm/router_utils/pre_call_checks/encrypted_content_affinity_check.py:256
↓ 10 callersMethod_ensure_adaptive_router
(self)
litellm/router_strategy/complexity_router/complexity_router.py:3228
↓ 10 callersFunction_entra_jwt
A JWT shaped like a real Entra access token, expiring ``expires_in_seconds`` from now.
tests/unit/proxy/db/test_prisma_client.py:274
↓ 10 callersFunction_enum_values
(model_group: str = "bedrock-claude-group")
tests/unit/integrations/test_prometheus_remaining_tokens_router_fallback.py:68
↓ 10 callersMethod_estimate_precise_input_tokens
Model-aware input token estimate for the project ITPM reservation, using ``litellm.token_counter`` -- the same approach the d
litellm/proxy/hooks/parallel_request_limiter_v3.py:3455
↓ 10 callersFunction_event
(event_type: str, **fields: object)
tests/unit/llms/soniox/realtime/test_soniox_realtime_transformation.py:37
↓ 10 callersFunction_exported_span
(logger, exporter)
tests/unit/integrations/test_langfuse.py:1653
↓ 10 callersFunction_extract_error_from_sse_chunk
Extract error dictionary from SSE format chunk. Args: event_line: SSE format event line, e.g. "data: {"error": {...}}\n\n" d
litellm/proxy/common_request_processing.py:1130
↓ 10 callersMethod_failure_handler_helper_fn
(self, exception, traceback_exception, start_time=None, end_time=None)
litellm/litellm_core_utils/litellm_logging.py:4594
↓ 10 callersFunction_failure_row
(call_id: str)
tests/integration/providers/test_bedrock_converse_stream_event_frames_wire.py:305
↓ 10 callersFunction_failure_usage_to_lift
( model_call_details: Mapping[str, object], request_body: Mapping[str, object], dispatched: bool,
litellm/proxy/utils.py:1559
↓ 10 callersMethod_fetch_oauth_metadata_from_resource
( self, resource_metadata_url: str, server_url: str )
litellm/proxy/mcp_server/mcp_server_manager.py:5359
↓ 10 callersMethod_filter_skipped_messages
( self, messages: Sequence[AllMessageValues] )
litellm/proxy/guardrails/guardrail_hooks/lakera_ai_v2.py:376
↓ 10 callersFunction_finish_reasons
(chunks: Sequence[Mapping[str, JsonValue]])
tests/integration/providers/test_anthropic_refusal_stop_details_wire.py:481
↓ 10 callersMethod_flush_deferred_async_logging
Fire the deferred async-success closure stored by wrapper_async, then clear the slot. Called from the finally block around p
litellm/proxy/common_request_processing.py:4362
↓ 10 callersFunction_full
(model: str)
tests/integration/providers/test_vertex_partner_count_tokens_wire.py:210
↓ 10 callersFunction_function_tool
(defer_loading: JsonValue = True)
tests/integration/providers/test_responses_bridge_tool_search_undeferred_wire.py:81
↓ 10 callersFunction_future_expires_at_ms
(offset_seconds: float = 3600)
tests/unit/llms/gigachat/test_authenticator.py:26
↓ 10 callersFunction_generate_key
(client: ManagementClient, resources: ResourceManager, body: KeyGenerateBody)
tests/e2e/management/test_management_e2e.py:68
↓ 10 callersFunction_generation
(client: LoggingClient, creds: LangfuseCreds, *, alias: str, started: datetime)
tests/e2e/logging/test_otel_v2_langfuse_generation_output_e2e.py:119
↓ 10 callersMethod_get_allowed_mcp_servers_for_key
Get the key's own MCP ceiling from its object_permission (mcp_servers, tag-style mcp_access_groups, mcp_tool_permissions). U
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:3570
↓ 10 callersFunction_get_cli_sso_flow_cache_key
(login_id: str)
litellm/proxy/management_endpoints/ui_sso.py:320
↓ 10 callersMethod_get_configured_bucket_name
(self, litellm_params: Mapping[str, object])
litellm/llms/vertex_ai/files/transformation.py:1231
↓ 10 callersMethod_get_embedding
Routes through the proxy Router when the embedding model is a Router deployment so per-deployment auth (e.g. Bedrock aws_role_name) a
litellm/caching/redis_semantic_cache.py:352
↓ 10 callersMethod_get_exception_class_name
(exception: Exception)
litellm/integrations/prometheus.py:3814
↓ 10 callersFunction_get_jwt_handler_with_issuer_keys
(issuers: list, keys_by_url: dict)
tests/unit/proxy/auth/test_handle_jwt.py:4175
↓ 10 callersMethod_get_log_exporter
Get the appropriate log exporter based on the configuration.
litellm/integrations/opentelemetry.py:3220
↓ 10 callersMethod_get_metric
Helper function to get a metric from the registry by name.
litellm/integrations/prometheus_services.py:169
↓ 10 callersMethod_get_model_from_gcs_file
Extracts the model from the gcs file uri When files are uploaded using LiteLLM (/v1/files), the model is stored in the gcs file uri
litellm/llms/vertex_ai/batches/transformation.py:400
↓ 10 callersMethod_get_openai_compatible_batch_metadata
OpenAI Batch metadata only accepts string values.
litellm/llms/bedrock/batches/transformation.py:380
↓ 10 callersFunction_get_public_model_name
Determine the public model name from patch or existing model. The top-level ``model_name`` is the rename channel. For team-scoped rows the DB
litellm/proxy/management_endpoints/model_management_endpoints.py:2337
↓ 10 callersFunction_get_response_for_spend_logs_payload
( payload: StandardLoggingPayload | None, kwargs: dict | None = None, )
litellm/proxy/spend_tracking/spend_tracking_utils.py:2148
↓ 10 callersFunction_get_rsa_key_and_jwk
(kid: str)
tests/unit/proxy/auth/test_jwt.py:1565
↓ 10 callersMethod_get_tools_by_names
Get tools from available_tools by their names, preserving the semantic router's ordering. Matching is tolerant of client-sid
litellm/proxy/mcp_server/semantic_tool_filter.py:396
↓ 10 callersMethod_get_trace_context
Get the New Relic trace ID for AI monitoring events. This integration runs in LiteLLM's async logging worker, outside the Ne
litellm/integrations/newrelic/newrelic.py:257
↓ 10 callersFunction_git
(cwd: Path, *args: str)
tests/unit/test_lint_workflow_diff_gates.py:198
↓ 10 callersFunction_github_http
Patch the shared async HTTP client to an httpx MockTransport that answers GitHub endpoints from {url: response-json dict or callable}; anything el
tests/unit/proxy/credential_endpoints/test_endpoints.py:2141
↓ 10 callersFunction_good_tx
(mock_batcher)
tests/unit/proxy/db/test_db_spend_update_writer.py:4100
↓ 10 callersFunction_google_reference
()
tests/unit/test_utils.py:7617
← previousnext →6,601–6,700 of 202,479, ranked by callers