MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 6 callersMethod_base
(self)
tests/integration/observability/test_straiker_v3_platform.py:395
↓ 6 callersFunction_base_config
()
tests/integration/authorization/test_hidden_alias_budget_bypass.py:359
↓ 6 callersFunction_base_row
(**overrides)
tests/unit/integrations/focus/test_focus_transformer.py:12
↓ 6 callersFunction_base_url
(owned: OwnedProxy)
tests/integration/providers/test_device_code_login_guard_boot.py:128
↓ 6 callersFunction_base_url
(gateway: Gateway)
tests/integration/providers/test_responses_minted_reasoning_replay_wire.py:126
↓ 6 callersFunction_batch
(spend: float, started_at: datetime | None = BATCH_STARTED_AT)
tests/unit/proxy/db/test_budget_window_spend_writer.py:136
↓ 6 callersFunction_batch_routes
( model: str, *, output_file: bool = True, metadata_fails: bool = False, )
tests/integration/management/test_batch_output_file_listing.py:103
↓ 6 callersFunction_batch_spend
(rig: Rig, key: str)
tests/integration/observability/test_batch_line_items_cold_storage.py:511
↓ 6 callersFunction_best_effort
Run a conversion, returning ``fallback`` unchanged if it raises.
litellm/proxy/a2a/version_convert.py:48
↓ 6 callersFunction_beta_transcription_body
(model: str)
tests/integration/providers/test_realtime_webrtc_http.py:492
↓ 6 callersFunction_beta_transcription_reply
(raw: str, expires_at: int)
tests/integration/providers/test_realtime_webrtc_http.py:499
↓ 6 callersFunction_bill_partial_streamed_spend_on_disconnect
A client disconnect throws GeneratorExit/CancelledError into the streaming generator, so neither the success nor the failure logging callback
litellm/proxy/common_request_processing.py:505
↓ 6 callersFunction_billed
(model: str)
tests/integration/providers/test_custom_prompt_template_wire.py:150
↓ 6 callersFunction_billed
(rows: Sequence[Mapping[str, JsonValue]])
tests/integration/mcp/test_mcp_llm_endpoints.py:1399
↓ 6 callersFunction_blocked_response_usage
Token usage for a synthetic guardrail-blocked response. A post-call block replaces the LLM's response with the violation message, but th
litellm/proxy/proxy_server.py:13157
↓ 6 callersFunction_body
(model: str, call: _Call)
tests/integration/providers/test_responses_bridge_tool_search_chaos.py:194
↓ 6 callersFunction_body
(route: Route, model: str, marker: str, **extra: JsonValue)
tests/integration/providers/test_cloudflare_clef_omni_media_wire.py:125
↓ 6 callersFunction_body_iterator
()
tests/unit/proxy/response_polling/test_response_polling_handler.py:1404
↓ 6 callersFunction_boot_from_config_file
(config_path: Path, *flags: str)
tests/unit/proxy/test_proxy_cli.py:4176
↓ 6 callersFunction_boot_proxy
( monkeypatch: pytest.MonkeyPatch, public_key: RSAPublicKey, env_license: str | None, license_
tests/unit/proxy/proxy_server/test_proxy_config.py:2712
↓ 6 callersFunction_bounded
(limit: int, awaitables: Sequence[Awaitable[_T]])
litellm/proxy/management_helpers/bulk_user_creation.py:417
↓ 6 callersFunction_bridge_key
(rig: BridgeRig)
tests/integration/mcp/test_mcp_llm_endpoints.py:1861
↓ 6 callersFunction_bridge_message_params
()
tests/unit/a2a_protocol/test_main.py:899
↓ 6 callersFunction_bridge_register_response
( server: "MCPServer", request_payload: _BridgeRegistrationPayload, replace_stale_client: bool = F
tests/unit/proxy/mcp_server/test_discoverable_endpoints.py:5862
↓ 6 callersFunction_bridge_rig
( hooked: Hooked, bridge: Bridge, lookup_description: str | Callable[[Mapping[str, str]], str] = LOOKUP[0]
tests/integration/mcp/test_mcp_llm_endpoints.py:1830
↓ 6 callersFunction_bridged_gpt
(scenario: Scenario, wire: Wire, **parameters: JsonValue)
tests/integration/providers/test_responses_bridge_verbosity_wire.py:75
↓ 6 callersFunction_bridged_output_items
(response, item_type)
tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py:5458
↓ 6 callersFunction_bucket
(kwargs: Mapping[str, object], name: str)
tests/unit/test_router/core/test_endpoints_characterization_generic.py:47
↓ 6 callersFunction_budget_lookup_by_id
A ``litellm_budgettable.find_unique`` double that serves the given budgets by id.
tests/unit/proxy/auth/test_auth_checks_object_access_and_lookup.py:8702
↓ 6 callersFunction_budget_reservation
()
tests/unit/rust_bridge/host/test_callbacks_legacy_python.py:96
↓ 6 callersFunction_budget_state
(team_id: str, user_id: str)
tests/integration/spend/test_team_member_spend.py:189
↓ 6 callersFunction_buffer_first_chunk_honoring_disconnect
Fetch the first streamed chunk, cancelling the upstream LLM call if the client disconnects before it arrives. create_response and the guarded
litellm/proxy/common_request_processing.py:1250
↓ 6 callersMethod_build_aim_inspection_messages
AIM validates against the OpenAI chat schema. Bare ``role: "tool"`` without ``tool_call_id`` and bare ``role: "function"`` without ``name``
litellm/proxy/guardrails/guardrail_hooks/aim/aim.py:204
↓ 6 callersMethod_build_block_error_detail
(self, message: str, armor_response: Mapping[str, object])
litellm/proxy/guardrails/guardrail_hooks/model_armor/model_armor.py:285
↓ 6 callersFunction_build_budget_limits_usage
Current-window spend per budget window, keyed by budget_duration, reported next to the stored budget_limits (which is returned untouched). No
litellm/proxy/management_endpoints/key_management_endpoints.py:4915
↓ 6 callersFunction_build_db_model_with_pricing
Wildcard deployment with custom pricing in litellm_params; Deployment.__init__ mirrors SPECIAL_MODEL_INFO_PARAMS into model_info, so both blobs ho
tests/unit/proxy/management_endpoints/test_model_management_endpoints.py:4149
↓ 6 callersMethod_build_logging_response
(self, armor_response: Mapping[str, object])
litellm/proxy/guardrails/guardrail_hooks/model_armor/model_armor.py:290
↓ 6 callersFunction_build_mock_response
Build a ResponsesAPIResponse that ``async_response_api_handler`` would return.
tests/unit/router_utils/pre_call_checks/test_encrypted_content_affinity_check.py:64
↓ 6 callersMethod_build_processing_obj
(self, custom_llm_provider: str, endpoint: str = "")
tests/unit/proxy/test_common_request_processing.py:6574
↓ 6 callersMethod_build_project_reservation_ops
( self, targets: Sequence[tuple[str, str]], reserved_scopes: Set[tuple[str, str]],
litellm/proxy/hooks/parallel_request_limiter_v3.py:4635
↓ 6 callersMethod_build_prompt_moderation_payload
Build the bare OpenAI request the before_prompt webhook consumes. Unlike the after_completion envelope, this endpoint takes a raw OpenAI
litellm/integrations/rubrik.py:617
↓ 6 callersMethod_build_request
(self, documents, top_n=None)
tests/unit/llms/nvidia_nim/rerank/test_nvidia_nim_rerank_transformation.py:197
↓ 6 callersMethod_build_reservation_aware_tpm_ops
Emit per-scope TPM increment ops with reservation awareness. - Reserved scope (counter already at +reserved from pre-call):
litellm/proxy/hooks/parallel_request_limiter_v3.py:4575
↓ 6 callersFunction_build_scope
( resolver: EntityScopeResolver, query: EntityQuery, entity_ids: Sequence[str] | None, exclude
litellm/proxy/management_endpoints/daily_activity_scopes.py:71
↓ 6 callersFunction_build_sso_user_update_data
Build the update data dictionary for SSO user upsert. Args: result: The SSO response containing user information user_email:
litellm/proxy/management_endpoints/ui_sso.py:2113
↓ 6 callersMethod_build_sts_client_kwargs
STS client kwargs with aligned endpoint_url and region_name (SigV4).
litellm/llms/bedrock/base_aws_llm.py:803
↓ 6 callersFunction_build_team_for_me
Real LiteLLM_TeamTableCachedObj as get_team_object would return.
tests/unit/proxy/management_endpoints/test_team_endpoints.py:12413
↓ 6 callersMethod_build_valkey_url
(host: str | None, port: str | None, password: str | None, ssl: bool = False)
litellm/caching/valkey_semantic_cache.py:105
↓ 6 callersFunction_cache_plan
(body: Mapping[str, JsonValue])
tests/unit/llms/anthropic/test_anthropic_prompt_cache_prediction.py:288
↓ 6 callersFunction_cache_temporary_mcp_server_in_redis
Best-effort write-through to Redis so temporary MCP OAuth sessions are shared across proxy instances. Keep local in-memory cache as f
litellm/proxy/management_endpoints/mcp_management_endpoints.py:531
↓ 6 callersFunction_cached_read_tokens
Cache-read tokens however the provider reports them: Anthropic-style ``cache_read_input_tokens`` or OpenAI-style ``prompt_tokens_details.cached_to
tests/e2e/llm_translation/test_cache_control.py:113
↓ 6 callersMethod_call
(self, **kwargs)
tests/unit/llms/nadir/test_nadir.py:213
↓ 6 callersFunction_call_azure_ai
(recorder: _RecordedAzureAI, **overrides)
tests/unit/llms/custom_httpx/test_llm_http_handler.py:4300
↓ 6 callersMethod_call_checkpoint
Call the Ovalix Tracker checkpoint API and return the JSON response. Both routes live on the tracker's /beta litellm router, which accepts th
litellm/proxy/guardrails/guardrail_hooks/ovalix/ovalix.py:229
↓ 6 callersFunction_call_id
(response: httpx.Response)
tests/integration/providers/test_bedrock_runtime_chat_completions_sad_wire.py:87
↓ 6 callersMethod_callbacks
The outcome callbacks that run for this attempt when its stream ends.
litellm/router_rust/invoke/streaming.py:197
↓ 6 callersFunction_caller_within_team_member_model_budget
( user_api_key_auth: "UserAPIKeyAuth", model_max_budget_limiter: _TeamMemberModelBudgetLimiter, mo
litellm/llms/anthropic/messages/caller_model_checks.py:329
↓ 6 callersFunction_calls_to
(calls: Sequence[Request], runtime: str)
tests/integration/providers/test_strands_decider_agentcore_wire.py:232
↓ 6 callersMethod_canary_request_metadata
Raw request metadata shaped like the proxy builds it, credentials included.
tests/unit/integrations/test_langfuse.py:586
↓ 6 callersFunction_candidate_ids
(router: Router, model: str)
tests/unit/router_strategy/test_router_routing_groups.py:397
↓ 6 callersFunction_capacity_test_metadata
(provider: str, max_input_tokens: int)
tests/unit/test_router_model_cost_isolation.py:3882
↓ 6 callersFunction_capture_image_edit_request
(captured)
tests/unit/images/test_image_edit_extra_params.py:17
↓ 6 callersFunction_capture_spend_events
(monkeypatch: pytest.MonkeyPatch)
tests/unit/proxy/response_api_endpoints/test_endpoints.py:1403
↓ 6 callersFunction_capturing_fetch
(response: InteractionsAPIResponse)
tests/unit/interactions/test_background_cost_polling.py:844
↓ 6 callersFunction_case
(*, surface: Surface = "sdk", function: SdkFunction = "ocr")
tests/rust-python-harness/strategies/trace_parity/test_runner.py:27
↓ 6 callersFunction_catalog
( gateway: Gateway, *, key: str | None = None, params: Mapping[str, str] | None = None )
tests/integration/compatibility/test_codex_model_catalog.py:109
↓ 6 callersFunction_catalog
(*model_ids: str)
tests/unit/llms/openrouter/test_openrouter_common_utils.py:24
↓ 6 callersFunction_catalog_response
( gateway: Gateway, *, key: str | None = None, params: Mapping[str, str] | None = None, he
tests/integration/compatibility/test_codex_model_catalog.py:83
↓ 6 callersMethod_challenge
( server: MCPServer | None, allowed: list[MCPServer], *, user: UserAPIKeyAuth
tests/unit/proxy/mcp_server/test_operations.py:1100
↓ 6 callersFunction_charged_spend
(user_id: str)
tests/integration/spend/test_end_user_spend_without_proxy_user.py:88
↓ 6 callersFunction_chat
(model: str, prompt: str, **extra: JsonValue)
tests/integration/providers/test_inferenceapis_wire.py:180
↓ 6 callersFunction_chat
(proxy: Gateway, model: str, key: str, text: str)
tests/integration/management/test_team_block.py:62
↓ 6 callersFunction_chat_answer
(response: httpx.Response)
tests/integration/providers/test_bedrock_converse_missing_content_wire.py:223
↓ 6 callersFunction_chat_payload
()
tests/unit/integrations/test_s3_v2.py:2711
↓ 6 callersFunction_chat_session_id
( monkeypatch: pytest.MonkeyPatch, litellm_params: Mapping[str, object], correlation_in_logs: bool
tests/unit/proxy/spend_tracking/test_spend_tracking_utils.py:586
↓ 6 callersFunction_chat_stream
(gateway: Gateway, body: Mapping[str, JsonValue])
tests/integration/streaming/test_fake_stream_reasoning_wire.py:278
↓ 6 callersFunction_chat_stream_response
(identity: str, calls: Sequence[dict[str, JsonValue]], *, include_usage: bool = True)
tests/integration/observability/_openinference_support.py:921
↓ 6 callersFunction_chat_text
(text: str)
tests/integration/streaming/test_stream_clean_eof_without_finish_reason.py:215
↓ 6 callersFunction_check_agent_url_health
Perform a GET request against the agent's URL and return the health result. Returns a dict with ``agent_id``, ``healthy`` (bool), and an opt
litellm/proxy/agent_endpoints/endpoints.py:271
↓ 6 callersMethod_check_and_emit_periodic_metric
Check if 27 hours have passed since last metric emission and re-emit if needed. Uses a mutex to ensure only one thread emits the met
litellm/integrations/newrelic/newrelic.py:236
↓ 6 callersMethod_check_is_valid_dict
Check 1: fetched map is a non-empty dict.
litellm/litellm_core_utils/get_model_cost_map.py:129
↓ 6 callersMethod_check_model_count_not_reduced
Check 2: model count has not reduced significantly vs backup.
litellm/litellm_core_utils/get_model_cost_map.py:147
↓ 6 callersMethod_check_streaming_has_ended
Check if streaming response has ended by looking for non-null stop_reason. Handles two formats: 1. Raw bytes in SSE (Server-
litellm/llms/anthropic/chat/guardrail_translation/handler.py:2162
↓ 6 callersFunction_check_team_admin_model_caps
( existing: Mapping[str, object], requested: Mapping[str, object], routed_models: RoutedModels = _
tests/unit/proxy/management_endpoints/test_team_endpoints.py:17643
↓ 6 callersFunction_chunk_choices
(item: object)
litellm/proxy/guardrails/guardrail_hooks/unified_guardrail/unified_guardrail.py:136
↓ 6 callersMethod_claim_pin
(self, cache_key: str, pin_value: DeploymentAffinityCacheValue, ttl_seconds: int)
litellm/router_utils/pre_call_checks/deployment_affinity_check.py:358
↓ 6 callersFunction_classifier_config
(judge_url: str, **overrides: JsonValue)
tests/integration/routing/test_complexity_router_databricks_classifier.py:159
↓ 6 callersMethod_classifier_config
(classifier: Mapping[str, object], legacy: bool)
tests/unit/proxy/management_endpoints/test_model_management_endpoints.py:9067
↓ 6 callersMethod_classifier_image_parts
Images from the newest user turn to hand the classifier, capped by max_images. Empty unless the operator opted in AND the classifier model is
litellm/router_strategy/complexity_router/complexity_router.py:2215
↓ 6 callersFunction_claude_count
( responses_request: dict[str, JsonValue], policy: DropPolicy )
tests/unit/responses/litellm_completion_transformation/test_count_request.py:72
↓ 6 callersFunction_claude_model
(scenario: Scenario, wire: Wire)
tests/integration/streaming/test_fake_stream_reasoning_wire.py:213
↓ 6 callersFunction_claude_output_row
(custom_id: str, text: str, content: object = None)
tests/unit/llms/vertex_ai/files/test_vertex_ai_files_transformation.py:2015
↓ 6 callersFunction_clean_db
Connects inside the running test's loop. An async fixture would be torn up on a different loop than the test body, which prisma's engine lock refu
tests/integration/management/test_access_group_team_sync.py:36
↓ 6 callersFunction_cleanup_config
(tmp_path: Path, retention: dict[str, JsonValue])
tests/integration/spend/test_daily_tag_spend_retention.py:97
↓ 6 callersMethod_clear_anthropic_env
(self, monkeypatch)
tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py:6681
↓ 6 callersFunction_cleared_bridge
( respx_mock: respx.MockRouter, monkeypatch: pytest.MonkeyPatch, *, stream: bool, edits: l
tests/unit/llms/anthropic/messages/responses_adapters/test_responses_adapters_handler.py:1058
↓ 6 callersFunction_cli_link
(proxy: Gateway, login_id: str)
tests/integration/authorization/test_cli_sso_login_ui_disabled.py:207
↓ 6 callersFunction_client
( sink: _RecordingSink | Callable[[], _RecordingSink | None], spawned: _Spawned, *, settle_timeout_s: floa
tests/unit/proxy/telemetry/test_middleware.py:93
↓ 6 callersFunction_client
(role: LitellmUserRoles)
tests/unit/proxy/agent_endpoints/test_agent_search.py:362
↓ 6 callersFunction_client
(caller: UserAPIKeyAuth)
tests/unit/proxy/search_endpoints/test_endpoints.py:40
← previousnext →11,601–11,700 of 202,479, ranked by callers