MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 8 callersFunctionhttp2_enabled
()
litellm/llms/custom_httpx/http_handler.py:86
↓ 8 callersFunctionhttp_config
()
litellm-rust/crates/inference-testing/src/lib.rs:34
↓ 8 callersFunctioni
(e=1)
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:1
↓ 8 callersFunctioni
(e,t,n,r)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 8 callersFunctioni5
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:55
↓ 8 callersFunctionid_jag_assertion_capture_gap
Why ID-JAG cannot work under the active SSO provider, phrased for an operator reading a log, or ``None`` when that provider does capture an assert
litellm/proxy/management_endpoints/sso/id_jag_assertion_capture.py:54
↓ 8 callersMethodidentify
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersFunctionidentity
(marker: str)
tests/integration/_support/anthropic_thinking.py:39
↓ 8 callersFunctionids_under_review
(classifier_request: Request)
tests/integration/_support/safeguards_rig.py:398
↓ 8 callersMethodincrement_deployment_usage_for_response
Count a response's tokens and request against its deployment, once the call returned, and note them on the request for the success callback (`
litellm/router_rust/surface/legacy_members.py:432
↓ 8 callersMethodindexAfter
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 8 callersMethodinitialize_from_proxy_config
Static method to initialize WebSearchInterceptionLogger from proxy config. Used in callback_utils.py to simplify initialization logi
litellm/integrations/websearch_interception/handler.py:1990
↓ 8 callersMethodinsert_with_deliveries
( self, rows: Sequence[Mapping[str, object]], *, write_spend_logs: bool = True )
litellm/repositories/table_repositories.py:132
↓ 8 callersFunctioninternal_sub_call
A nested call the parent call logs and bills, so the parent must fold this call's cost into its own.
litellm/_internal_context.py:53
↓ 8 callersFunctioninterpret
What redis-py's constructors make of kwargs a host already merged the way `_get_redis_client_logic` does. A host passes its `credential_provider` obje
litellm-rust/crates/redis-resolve/src/lib.rs:45
↓ 8 callersMethodinto_stream
(self)
litellm-rust/crates/gateway-forward/tests/support/mod.rs:187
↓ 8 callersMethodinvalidate
(&self, key: &K)
litellm-rust/crates/secrets-types/src/cache.rs:45
↓ 8 callersMethodinvalidate_user_oauth_token_cache
Drop every cached token for ``(user_id, server_id)`` after the credential row changes (re-auth, revoke, config-change purge): the v2 chain's c
litellm/proxy/mcp_server/mcp_server_manager.py:6918
↓ 8 callersFunctioniq
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 8 callersFunctionir_to_systemone_response
(response: DecisionsIRResponse, request: DecisionsIRRequest)
litellm/llms/base_llm/decisions/transformation.py:481
↓ 8 callersFunctionisIndexed
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersMethodisObject
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersFunctionis_agentic_followup_failure
(error: BaseException)
litellm/litellm_core_utils/agentic_followup_failure.py:25
↓ 8 callersFunctionis_anthropic_tool_search_chat_tool
(tool: object)
litellm/responses/litellm_completion_transformation/tool_search.py:131
↓ 8 callersMethodis_auth_enforced_pass_through_route
True for config/DB pass-through endpoints registered with auth=true. These routes are injected into ``openai_routes`` for spend/budg
litellm/proxy/auth/route_checks.py:780
↓ 8 callersMethodis_debug_enabled
Check if the client opted into MCP debug mode. Looks for ``x-litellm-mcp-debug: true`` (case-insensitive) in the request hea
litellm/proxy/mcp_server/mcp_debug.py:250
↓ 8 callersFunctionis_encrypted_reasoning_block
A thinking or redacted_thinking block carrying Responses API encrypted reasoning. Only the Responses API that minted the content can read it back
litellm/litellm_core_utils/prompt_templates/reasoning_utils.py:184
↓ 8 callersMethodis_error_str_rate_limit
Check if an error string indicates a rate limit error. Args: error_str: The error string to check status_cod
litellm/litellm_core_utils/exception_mapping_utils.py:52
↓ 8 callersMethodis_gemini_3_or_newer
( cls, model: str, )
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:853
↓ 8 callersFunctionis_gemini_image_model
(model: str)
litellm/llms/gemini/common_utils.py:149
↓ 8 callersMethodis_license_acceptable
Check if a license (or compound SPDX expression) is acceptable.
tests/code_coverage_tests/check_licenses.py:215
↓ 8 callersFunctionis_non_conversational_call_type
Return True if ``call_type``'s body carries no conversation to inspect.
litellm/proxy/guardrails/_content_utils.py:65
↓ 8 callersFunctionis_passthrough_list_route
Return True when this is a GET list route whose results should be served from the DB (user-scoped) rather than forwarded upstream.
litellm/proxy/pass_through_endpoints/managed_id_rewriter.py:947
↓ 8 callersFunctionis_prompt_caching_valid_prompt
Returns true if the prompt is valid for prompt caching. The minimum cacheable prefix is per-model, so it is resolved from `model` unless the
litellm/utils.py:11792
↓ 8 callersMethodis_registered_pass_through_route
Check if route is a registered pass-through endpoint from DB Uses the in-memory registry to avoid additional DB queries Opti
litellm/proxy/pass_through_endpoints/pass_through_endpoints.py:4096
↓ 8 callersFunctionis_resource_list
(section: Section, key: str)
litellm/proxy/config_resolvers/settings_rules.py:85
↓ 8 callersFunctionis_server_derived_pricing_key
Whether ``/model/info`` can fill ``key`` into ``model_info`` from the cost map. Two sources, because ``get_model_info`` emits two: the declared p
litellm/types/utils.py:4368
↓ 8 callersFunctionis_web_search_tool
Check if a tool is a web search tool (native or LiteLLM standard). Detects: - LiteLLM standard: name == "litellm_web_search" - OpenA
litellm/integrations/websearch_interception/tools.py:242
↓ 8 callersFunctionjson_response
(body: dict[str, JsonValue], status: int = 200)
tests/integration/compatibility/_status_code_audit.py:127
↓ 8 callersFunctionjson_response
(body: Value)
litellm-rust/crates/inference-messages/tests/support/mod.rs:62
↓ 8 callersFunctionjsonl
(*rows: Mapping[str, object])
tests/unit/proxy/batches_endpoints/test_litellm_executed_batches.py:71
↓ 8 callersMethodjwt
(self, subject: str, *team_ids: JsonValue)
tests/integration/authorization/test_rag_team_provider_credentials.py:146
↓ 8 callersFunctionk
(t)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 8 callersMethodkey_metadata
( self, api_keys: frozenset[str], window: SpendLogsWindow | None )
litellm/repositories/daily_activity_repository.py:284
↓ 8 callersFunctionkeys_at_every_depth
(value: object)
tests/_support/stream_chunk_size.py:28
↓ 8 callersFunctionl
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:1
↓ 8 callersFunctionlegacy_call
A legacy call over the namespace's `kwargs` and `bound` dicts, each empty when absent.
litellm-rust/crates/callbacks-legacy-python/src/test_support.rs:188
↓ 8 callersMethodline
(&mut self)
litellm-rust/crates/gateway-forward/tests/support/mod.rs:275
↓ 8 callersFunctionlist_fault_http_status
The truthful HTTP status for a single-upstream listing fault per RFC 9110: the upstream's own 401/403 for auth, 504 for a timeout, 502 for an unre
litellm/proxy/mcp_server/faults/list_outcomes.py:349
↓ 8 callersFunctionlist_guardrail_submissions
List team guardrail submissions. Returns only guardrails with a team_id. Admins see all submissions. Non-admin users see submissions for tea
litellm/proxy/guardrails/guardrail_endpoints.py:933
↓ 8 callersFunctionlist_vector_stores
List all available vector stores with optional filtering and pagination. Combines both in-memory vector stores and those stored in the databa
litellm/proxy/vector_store_endpoints/management_endpoints.py:357
↓ 8 callersFunctionlive
( entries: &Mutex<Vec<(K, W)>>, upgrade: fn(&W) -> Option<V>, )
litellm-rust/crates/redis-connect/src/hosts.rs:82
↓ 8 callersFunctionload_mcp_client_allowlist
None when ``mcp_allowed_clients`` is unset, which admits every client.
litellm/proxy/mcp_server/client_allowlist.py:114
↓ 8 callersFunctionload_openapi_spec_async
(filepath: str, *, max_bytes: int | None = None)
litellm/proxy/mcp_server/openapi_to_mcp_generator.py:309
↓ 8 callersFunctionload_session
( credentials: Credentials, session_id: str, cache_dir: Path, fetch: Fetch = fetch_session,
litellm/proxy/client/cli/commands/statusline_script.py:265
↓ 8 callersFunctionload_token
The stored credential as a plain mapping, with the secret resolved out of the vault. The PKCE renewal and revocation helpers read records by fiel
litellm/proxy/client/cli/commands/auth.py:229
↓ 8 callersMethodlock
(self, key: int = GATE_KEY)
tests/e2e/migrations/database.py:124
↓ 8 callersMethodlock
(&self)
litellm-rust/crates/http/src/pool.rs:98
↓ 8 callersMethodlog_success_event
(self, kwargs, response_obj, start_time, end_time)
litellm/integrations/braintrust_logging.py:135
↓ 8 callersMethodlogged_spend
(self)
tests/unit/a2a_protocol/test_main.py:833
↓ 8 callersFunctionm
()
litellm/proxy/_experimental/out/_next/static/chunks/11et800l-khs-.js:49
↓ 8 callersMethodm
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:11
↓ 8 callersFunctionmanaged_inference_request
( route: str, body: Mapping[str, object], settings: Mapping[str, object], cli_model: str | Non
litellm/proxy/agent_endpoints/auth/managed_authorization.py:110
↓ 8 callersMethodmap_openai_params
( self, non_default_params: dict, optional_params: dict, model: str, d
litellm/llms/gemini/image_generation/transformation.py:59
↓ 8 callersMethodmap_openai_params
( self, non_default_params: dict, optional_params: dict, model: str, d
litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude_transformation.py:172
↓ 8 callersMethodmap_openai_params
( self, non_default_params: dict, optional_params: dict, model: str, d
litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/transformation.py:240
↓ 8 callersMethodmap_openai_params
( self, video_create_optional_params: VideoCreateOptionalRequestParams, model: str,
litellm/llms/minimax/videos/transformation.py:497
↓ 8 callersFunctionmap_v3_rate_limit_type
Map the v3 rate limiter's internal `status["rate_limit_type"]` strings onto the public :class:`RateLimitType` enum. The v3 limiter uses
litellm/proxy/common_utils/proxy_rate_limit_error.py:75
↓ 8 callersFunctionmarker_of
(request: Request)
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_safeguards_beta_wire.py:86
↓ 8 callersFunctionmcpServersForIdentifier
(allServers: readonly MCPServer[], identifier: string)
ui/litellm-dashboard/src/components/mcp_server_management/effectiveMcpServers.ts:76
↓ 8 callersFunctionmcp_oauth_token_identity
The upstream-OAuth-token-determining fields of an MCP server: the resource/audience (url, or spec_path for OpenAPI servers, plus the RFC 8707 upst
litellm/proxy/mcp_server/db.py:1968
↓ 8 callersMethodmean
(self)
tests/e2e/perf/setup/telemetry.py:41
↓ 8 callersMethodmerge_prompt_management_input
( original_input: str | ResponseInputParam, client_input: list[AllMessageValues], merg
litellm/responses/utils.py:182
↓ 8 callersMethodmessages
( self, key: str, model: str, text: str, *, guardrails: list[s
tests/e2e/guardrails/guardrails_client.py:467
↓ 8 callersFunctionmessages_binding
(native: NativeMessages | None)
tests/test_litellm_rust/messages/test_dispatch.py:31
↓ 8 callersFunctionmessages_for_routing
Messages to use for a routing decision, per `policy.routing`. None means the caller should route on whatever it already has. Reads the live m
litellm/proxy/guardrails/auto_router_compression.py:205
↓ 8 callersFunctionmint_reasoning_item_id
()
litellm/responses/litellm_completion_transformation/reasoning_items.py:14
↓ 8 callersFunctionmock_post
(self, url, data=None, headers=None, **kwargs)
tests/unit/llms/bedrock/test_mantle.py:398
↓ 8 callersMethodmodel
(self, mode: Mode)
tests/integration/providers/test_responses_bridge_input_audio_wire.py:47
↓ 8 callersFunctionmodelInfoBody
(displayName string)
terraform/provider/litellm/resource_model_test.go:18
↓ 8 callersFunctionmodel_access_denied_client_message
(model: str | list[str])
litellm/proxy/auth/model_access_denied.py:16
↓ 8 callersFunctionmodel_info_as_mapping
A DB row's model_info column arrives as a dict or as its JSON string depending on the query path, and every consumer needs the mapping. Single own
litellm/proxy/management_endpoints/model_management_endpoints.py:3904
↓ 8 callersFunctionnZ
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 8 callersFunctionno_ttl
()
litellm-rust/crates/cache-azure-blob/tests/cache.rs:55
↓ 8 callersMethodnodes
(&self)
litellm-rust/crates/redis-testing/src/cluster.rs:73
↓ 8 callersFunctionnormalizeTierModels
(value: unknown)
ui/litellm-dashboard/src/components/add_model/complexity_router_tiers.ts:59
↓ 8 callersFunctionnormalize_gemini_speech_config
( value: Mapping[str, object], drop_unknown_fields: bool = False )
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:518
↓ 8 callersFunctionnormalize_root_paths
Strip whitespace and trailing slashes, dedupe, order longest-first; warn and drop entries missing a leading ``/`` and the bare root.
litellm/proxy/middleware/per_request_root_path_middleware.py:56
↓ 8 callersMethodnow
(&self)
litellm-rust/crates/router-core/src/health.rs:50
↓ 8 callersFunctiono
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:57
↓ 8 callersFunctiono
(r)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 8 callersFunctionobjMap
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersMethodobserve
(self, event: Mapping[str, object])
litellm/llms/anthropic/messages/safeguards.py:552
↓ 8 callersFunctionobserved
(core: RouterCore)
tests/unit/test_router/core/test_request_scoped_outcomes.py:97
↓ 8 callersFunctionocr_route
()
litellm-rust/crates/inference-ocr/tests/ocr/main.rs:43
↓ 8 callersMethodof
(self, alias: str)
tests/integration/authorization/test_agent_denial_logging.py:64
↓ 8 callersFunctiononBlur
(e)
litellm/proxy/_experimental/out/_next/static/chunks/1nj306n5h0tsy.js:1
↓ 8 callersFunctionone_delivery
(wire: Wire, marker: str)
tests/integration/providers/_anthropic_safeguards_beta_support.py:212
↓ 8 callersFunctiononlyVisible
(locator: Locator)
tests/e2e/ui/helpers/playground.ts:5
↓ 8 callersMethodopen
()
ui/litellm-dashboard/src/app/(dashboard)/playground/components/chat_ui/RealtimePlayground.test.tsx:37
← previousnext →9,401–9,500 of 202,479, ranked by callers