MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 42 callersMethodeq
(t)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 42 callersFunctionexhausted_key
(rig: AliasRig, scenario: Scenario)
tests/integration/authorization/_hidden_alias_budget.py:199
↓ 42 callersMethodget_api_base
(api_base: str | None = None)
litellm/llms/baseten/chat.py:107
↓ 42 callersMethodget_proxy_hook
Get a proxy hook from the proxy_hook_mapping
litellm/proxy/utils.py:2166
↓ 42 callersMethodmodel_copy
(self, *, update: Mapping[str, object])
litellm/responses/litellm_completion_transformation/streaming_iterator.py:88
↓ 42 callersMethodmodel_dump
(self)
litellm/llms/openai/common_utils.py:101
↓ 42 callersMethodmodel_list
`_core_get_model_list`: the name's deployments, its alias rows and routing group rows, its wildcard routes when nothing else serves it, or (no name) e
litellm-rust/crates/router-core/src/lookup.rs:314
↓ 42 callersFunctionopenai_error_param
OpenAI types ``error.param`` as nullable, so an exception carrying none serializes as JSON ``null``.
litellm/proxy/common_utils/openai_error_payload.py:118
↓ 42 callersFunctionpatch_model
PATCH Endpoint for partial model updates. Only updates the fields specified in the request while preserving other existing values. Follo
litellm/proxy/management_endpoints/model_management_endpoints.py:1682
↓ 42 callersMethodretrieve_batch
( self, batch_id: str, *, key: str, provider: str | None = None )
tests/e2e/batches/batch_client.py:210
↓ 42 callersMethodrun
(self)
tests/unit/litellm_core_utils/test_realtime_streaming.py:4854
↓ 42 callersFunctionshared_cache
A ``UserApiKeyCache`` with ``enable_redis_auth_cache`` on, its shared store backed by ``fake``.
tests/unit/redis/stores/auth_cache_double.py:166
↓ 42 callersMethodtransform_rerank_response
( self, model: str, raw_response: httpx.Response, model_response: RerankRespon
litellm/llms/voyage/rerank/transformation.py:99
↓ 42 callersMethodunregister
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 42 callersMethodwrite
(self, buffer: Buffer, /)
tests/integration/_support/wire.py:146
↓ 41 callersFunctionO
litellm/proxy/_experimental/out/_next/static/chunks/2s7apn3nfa3q3.js:1
↓ 41 callersMethod_bridge_delegate_server
(server_name="bridge_delegate_server", dcr_bridge=True, alias=None)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:6562
↓ 41 callersFunction_gateway_env
( *, enabled: bool = True, managed_settings: Mapping[str, object] | None = None, cache: DualCa
tests/unit/proxy/anthropic_endpoints/test_gateway_endpoints.py:158
↓ 41 callersFunction_make_chunk
(delta: Delta, finish_reason: Optional[str] = None)
tests/unit/llms/anthropic/messages/adapters/test_streaming_iterator_first_delta.py:46
↓ 41 callersFunction_make_request
(**overrides)
tests/unit/llms/anthropic/messages/responses_adapters/test_responses_adapters_transformation.py:42
↓ 41 callersFunction_sent
(host: ScriptedHost, index: int = -1)
tests/unit/test_router/core/test_endpoints_characterization_inference.py:30
↓ 41 callersFunction_token_response
(access_token: str = "obo-access-token", expires_in: int = 3599)
tests/unit/proxy/guardrails/guardrail_hooks/test_agent_365.py:48
↓ 41 callersMethodcheck_and_fix_namespace
Make sure each key starts with the given namespace
litellm/caching/redis_cache.py:764
↓ 41 callersFunctione
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 41 callersMethodhex
(&mut self, count: usize)
litellm-rust/crates/python-compat/src/literal.rs:626
↓ 41 callersMethodlen
(&self)
litellm-rust/crates/redis-store/src/memory.rs:53
↓ 41 callersMethodmodel_dump_json
(self, *, exclude_none: bool = ...)
litellm/responses/streaming_iterator.py:1597
↓ 41 callersMethodobserve
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 41 callersFunctionperform
(request: LiteLLMOcrRequest)
litellm-rust/crates/inference-ocr/tests/ocr/main.rs:60
↓ 41 callersMethodrecv
(self)
litellm/llms/openai/live/handler.py:98
↓ 41 callersFunctionresolve_openai_workload_identity_config
( api_key: str | None, api_base: str | None, litellm_params: Mapping[str, object] | None = None, )
litellm/llms/openai/workload_identity.py:61
↓ 41 callersMethodtransform_audio_transcription_response
(self, raw_response)
tests/unit/llms/custom_httpx/test_llm_http_handler.py:3006
↓ 41 callersFunctionupdate_key_fn
Update an existing API key's parameters. The body is a merge patch: a field left out keeps its stored value, and on the key's own columns
litellm/proxy/management_endpoints/key_management_endpoints.py:4021
↓ 41 callersMethodwait_for_async
(self, name: str, count: int = 1, timeout: float = 10)
tests/test_litellm_rust/support/callback_recorder.py:78
↓ 40 callersFunctionA
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0w-7k3irqo_46.js:1
↓ 40 callersFunctionH
({initialValues:e,describeField:r,isSaving:a,onSubmit:t})
litellm/proxy/_experimental/out/_next/static/chunks/1a2lzi3ursud4.js:1
↓ 40 callersMethod_build_responses_api_response_id
Build the responses_api_response_id
litellm/responses/utils.py:726
↓ 40 callersFunction_managed_files_hook
(store_side_effect: Any = None)
tests/unit/proxy/pass_through_endpoints/test_managed_id_rewriter.py:370
↓ 40 callersFunction_mantle_bodies
(wire: Wire)
tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py:332
↓ 40 callersFunction_request
(path="/authorize", query="", cookies=None, method="GET")
tests/unit/proxy/mcp_server/test_gateway_dcr_flow.py:85
↓ 40 callersFunction_scan
(tmp_path: Path, sql: str)
tests/unit/test_check_migrations_no_data_rewrites.py:23
↓ 40 callersFunction_send
(gateway: Gateway, body: dict[str, JsonValue], *, key: str | None = None)
tests/integration/providers/test_responses_bridge_message_cache_control_wire.py:130
↓ 40 callersMethodall
`_core_get_all_deployments`: the team's deployments under public name `model_name`, else the group's, else (for a team) every deployment the name incl
litellm-rust/crates/router-core/src/lookup.rs:195
↓ 40 callersMethodanthropic
(self, key: str)
tests/e2e/llm_translation/sdk_clients.py:52
↓ 40 callersFunctionanthropic_server_tool_call_params
(message: object)
litellm/llms/anthropic/common_utils.py:2314
↓ 40 callersFunctionapply_compact_20260112
Apply ``compact_20260112``; return a ``PolyfillResult``. See module docstring for the algorithm. Errors are best-effort: when the summary cal
litellm/llms/anthropic/messages/context_management/editors/compact.py:650
↓ 40 callersMethodasync_get_cache
( self, key: str, parent_otel_span: Span | None = None, local_only: bool = Fal
litellm/proxy/common_utils/user_api_key_cache.py:233
↓ 40 callersMethodasync_logging_hook
( self, kwargs: dict[str, object], result: object, call_type: str, )
tests/unit/proxy/guardrails/test_guardrail_endpoints.py:208
↓ 40 callersFunctionawait_entry
(store: Redis[bytes], needle: str)
tests/integration/caching/response_cache_case.py:297
↓ 40 callersMethodclose
(self)
litellm/proxy/auth/handle_jwt.py:1417
↓ 40 callersFunctioncollisions
(sources: Mapping[str, str])
tests/code_coverage_tests/check_workflow_job_name_collisions.py:486
↓ 40 callersFunctioncompute_savings_spend
Dollar savings for one request, split by optimization driver. Compression savings price the tokens compression removed at the model's in
litellm/proxy/spend_tracking/savings.py:596
↓ 40 callersMethodconvert_chat_completion_messages_to_responses_api
( self, messages: list["AllMessageValues"], *, drop_params: bool = False,
litellm/completion_extras/litellm_responses_transformation/transformation.py:972
↓ 40 callersFunctioncopyToClipboard
( text: string | null | undefined, messageText: string = i18n.t("utils.dataUtils.copiedToClipboard"), )
ui/litellm-dashboard/src/utils/dataUtils.ts:68
↓ 40 callersMethodencode
(self)
litellm/llms/bedrock/passthrough/guardrail_translation/handler.py:841
↓ 40 callersFunctionhealth_endpoint
🚨 USE `/health/liveliness` to health check the proxy 🚨 See more 👉 https://docs.litellm.ai/docs/proxy/health Check the health of all th
litellm/proxy/health_endpoints/_health_endpoints.py:1558
↓ 40 callersFunctionkey_metadata
( *, alias: str | None = None, team: str | None = None, user: str | None = None, email: st
tests/integration/_support/daily_activity.py:254
↓ 40 callersMethodlog
(self)
tests/integration/routing/test_per_model_rate_limit_fallbacks.py:77
↓ 40 callersFunctionmake_ctx
( sandbox: FakeSandbox | None = None, *, model: str | None = MODEL, gateway: GatewayTarget | N
tests/unit/llms/pi/harness/test_transformation.py:205
↓ 40 callersFunctionmake_ui_spend_logs_mock_prisma
Create a MockPrismaClient for /spend/logs/ui endpoint tests. Args: mock_spend_logs: List of mock spend log dicts. filter_fn:
tests/unit/proxy/spend_tracking/test_spend_management_endpoints.py:215
↓ 40 callersFunctionmap_finish_reason
(finish_reason: str)
litellm/litellm_core_utils/core_helpers.py:430
↓ 40 callersFunctionname
(cell: str)
tests/integration/observability/test_prometheus_provider_auth_failure.py:104
↓ 40 callersFunctionopen_stream
(core: RouterCore, **request: object)
tests/unit/test_router/core/test_streaming_characterization_responses.py:80
↓ 40 callersMethodregistry
The registry view, built once (``registry()`` returns the same object each time).
litellm/router_rust/core.py:1921
↓ 40 callersMethodreload_servers_from_database
(self)
litellm/proxy/mcp_server/mcp_server_manager.py:7342
↓ 40 callersFunctionreply_text
(marker: str)
tests/integration/providers/_api_base_trailing_slash_support.py:43
↓ 40 callersMethodresolve_credentials
(self, subject: Subject, server: ServerSpec)
litellm/proxy/mcp_server/outbound_credentials/resolver.py:153
↓ 40 callersMethodrun
(e,n,r)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 40 callersFunctionrun_agent
Validate, wire the environment, and hand off to the agent. On success this replaces the current process and never returns. Raises AgentRunErr
litellm/proxy/client/cli/commands/agents.py:1085
↓ 40 callersFunctionrun_async_fallback
Loops through all the fallback model groups and calls kwargs["original_function"] with the arguments and keyword arguments provided. If the
litellm/router_utils/fallback_event_handlers.py:791
↓ 40 callersMethodshield
(url: str, headers: dict, json: dict, timeout: float)
tests/unit/proxy/guardrails/guardrail_hooks/test_llm_shield_proxy.py:2019
↓ 40 callersMethodspend_counters
(self)
litellm/redis/stores/connection.py:33
↓ 40 callersFunctiontool_use_ids
(response_body: Mapping[str, JsonValue])
tests/integration/_support/safeguards_rig.py:377
↓ 40 callersMethodtransform_embedding_response
( self, model: str, raw_response: httpx.Response, model_response: EmbeddingRes
litellm/llms/oci/embed/transformation.py:258
↓ 39 callersFunctionR
({userData:e,onCancel:t,onSubmit:l,teams:o,accessToken:c,userID:z,userRole:I,userModels:T,possibleUIRoles:V,is
litellm/proxy/_experimental/out/_next/static/chunks/37cr8te-omsl0.js:1
↓ 39 callersFunction_config
(entra_token_minter=None)
tests/unit/llms/azure/search/test_bing_grounding_search_transformation.py:27
↓ 39 callersFunction_embed
(proxy: Gateway, model: str, text: JsonValue, **fields: JsonValue)
tests/integration/providers/test_sagemaker_embedding_wire.py:151
↓ 39 callersMethod_ensure_access_token
Returns auth token and project id
litellm/llms/vertex_ai/vertex_llm_base.py:626
↓ 39 callersFunction_model
(scenario: Scenario, provider: Wire, model: str = "openai/gpt-4o-mini")
tests/integration/observability/test_azure_content_safety_dispatch.py:60
↓ 39 callersFunction_payload
(marker_hex: str)
tests/integration/providers/test_vertex_anthropic_structured_output_wire.py:240
↓ 39 callersFunction_start_request
(**overrides: object)
tests/unit/proxy/management_endpoints/test_auto_router_endpoints.py:1707
↓ 39 callersFunction_v3_mock
(body: dict)
tests/unit/proxy/guardrails/guardrail_hooks/test_straiker.py:1137
↓ 39 callersFunction_wrap_entries
Vertex rows for a list of OpenAI batch entries, built via the live single-entry transform that the streaming upload path uses.
tests/unit/llms/vertex_ai/files/test_vertex_ai_files_transformation.py:956
↓ 39 callersFunctionactivity_of_key
( gateway: Gateway, path: str, api_key: str, *, reader: str | None = None, **filters: str )
tests/integration/_support/daily_activity.py:85
↓ 39 callersFunctionassert_free_row
(row: Mapping[str, JsonValue], model_group: str)
tests/integration/authorization/_hidden_alias_budget.py:272
↓ 39 callersFunctionasync_data_generator
( response, user_api_key_dict: UserAPIKeyAuth, request_data: dict, request: Request | None = N
litellm/proxy/proxy_server.py:10815
↓ 39 callersMethodasync_set_cache
(self, key: str, value: float, **kwargs: object)
tests/unit/router_strategy/test_budget_limiter_hotpath.py:494
↓ 39 callersMethodbody
Reads exactly `length` body bytes, using what is already buffered first.
litellm-rust/crates/gateway-forward/tests/support/mod.rs:252
↓ 39 callersFunctioncall_retrieve
( harness: RetrieveHarness, batch_id: str, *, provider: Optional[str] = None, user: Option
tests/unit/proxy/batches_endpoints/test_endpoints.py:1554
↓ 39 callersMethodcall_tool
( self, params, host_progress_callback=None, raise_on_error=False, all
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:12175
↓ 39 callersMethodcalls
The LLM calls the deployment took; the proxy's boot-time ``GET /v1/models`` discovery of a config deployment is not one.
tests/integration/caching/response_cache_case.py:233
↓ 39 callersFunctionchat_body
(group: str, marker: str, **extra: JsonValue)
tests/integration/routing/test_priority_scheduler_queue_cleanup.py:243
↓ 39 callersMethodcommon_processing_pre_call_logic
( self, request: Request, general_settings: dict, user_api_key_dict: UserAPIKe
litellm/proxy/common_request_processing.py:2530
↓ 39 callersMethodcreate
(self, **_kwargs)
tests/unit/llms/openai/test_openai.py:2076
↓ 39 callersMethodemit
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/3lb5gjzjxjxem.js:1
↓ 39 callersFunctionencrypted_reasoning_signature
The opaque value a Responses API reasoning item's `encrypted_content` travels in. Anthropic clients echo a thinking block's `signature` and a red
litellm/litellm_core_utils/prompt_templates/reasoning_utils.py:66
↓ 39 callersMethoderrors
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 39 callersMethodfilter_anthropic_output_schema
Filter out unsupported fields from JSON schema for Anthropic's output_format API. Anthropic's output_format doesn't support certain
litellm/llms/anthropic/chat/transformation.py:916
↓ 39 callersMethodfind_first
( self, *, where: Mapping[str, object], include: Mapping[str, object] | None = None )
litellm/proxy/auth/auth_checks.py:258
↓ 39 callersFunctionfresh
A scripted outcome that raises a new error per call, so stamps from one call never leak into the next.
tests/unit/test_router/core/test_retries_cooldowns.py:58
← previousnext →1,101–1,200 of 202,479, ranked by callers