MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 9 callersMethodcount
(e={},t)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:14
↓ 9 callersMethodcount_billable_users
Number of users that count toward the license seat limit. Every user is billable except those SCIM-deactivated (metadata.scim_active
litellm/repositories/user_repository.py:159
↓ 9 callersFunctioncount_entry_tokens
Token-count a single batch input entry's body (chat / text / embedding).
litellm/batches/batch_utils.py:741
↓ 9 callersMethodcreate
( self, data: Mapping[str, object], include: Mapping[str, bool] | None = N
litellm/proxy/management_endpoints/customer_endpoints.py:91
↓ 9 callersMethodcreate
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:14
↓ 9 callersFunctioncreateApiClient
(config: ApiClientConfig)
ui/litellm-dashboard/src/lib/http/client.ts:151
↓ 9 callersFunctioncreateNamespace
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 9 callersFunctioncreateVirtualKey
( request: APIRequestContext, data: Record<string, unknown> = {}, )
tests/e2e/ui/helpers/traffic.ts:86
↓ 9 callersMethodcreate_container
(&self)
litellm-rust/crates/cache-azure-blob/src/cache.rs:102
↓ 9 callersMethodcreate_counter
( self, service: str, type_of_request: str, additional_labels: list[str] | Non
litellm/integrations/prometheus_services.py:196
↓ 9 callersMethodcreate_key_deleted_audit_logs
( keys_being_deleted: Sequence["LiteLLM_VerificationToken | prisma_models.LiteLLM_VerificationToken"],
litellm/proxy/hooks/key_management_event_hooks.py:256
↓ 9 callersFunctioncreate_scratch_user
( db: ManagementDatabase, scratch_prefix: str, *, suffix: str, user_email: str | None = No
tests/integration/_support/actors.py:325
↓ 9 callersMethodcreate_team
( self, alias: str, *, models: list[str], organization_id: str | None
tests/e2e/logging/logging_client.py:338
↓ 9 callersMethodcreate_team
(self, body: TeamNewBody)
tests/e2e/management/management_client.py:322
↓ 9 callersFunctioncredential_gated_exporters
``exporters`` with the operator's destination replaced by a header-gated one. Used when a credential-mandatory backend is asked to build without
litellm/integrations/otel/presets/utils.py:22
↓ 9 callersFunctioncustom_prompt
( role_dict: Mapping[str, Mapping[str, str]], messages: list, initial_prompt_value: str = "",
litellm/litellm_core_utils/prompt_templates/factory.py:6168
↓ 9 callersFunctiondeclare_mid_conversation_system
(monkeypatch: pytest.MonkeyPatch)
tests/unit/conftest.py:486
↓ 9 callersFunctiondecode
(raw: bytes)
tests/integration/observability/test_bedrock_invoke_stream_post_call_guardrail.py:148
↓ 9 callersMethoddecode_encrypted_item_id
Decode a litellm-encoded encrypted-content item ID. Returns a dict with ``model_id`` and ``item_id`` keys, or ``None`` if the string
litellm/responses/utils.py:497
↓ 9 callersMethoddecode_previous_response_id_to_original_previous_response_id
Decode the previous_response_id to the original previous_response_id Why? - LiteLLM encodes the `custom_llm_provider` an
litellm/responses/utils.py:816
↓ 9 callersFunctiondecode_spend_event
(line: bytes)
litellm/proxy/spend_tracking/spend_event.py:387
↓ 9 callersFunctiondecoded
(video_id: str)
tests/integration/providers/_dashscope_video_support.py:100
↓ 9 callersMethoddecrypt_model_list_from_db
(self, new_models: list)
litellm/proxy/proxy_server.py:8027
↓ 9 callersFunctiondecrypted_response_id
The id a client-facing response id stands for, the same for every encryption of one response.
litellm/proxy/hooks/responses_id_security.py:480
↓ 9 callersFunctiondel
One multi-key `DEL`, no round trip for no keys. Pipelined, every key must share a hash slot.
litellm-rust/crates/redis-client/src/commands.rs:264
↓ 9 callersMethoddelete_key_strict
Strict delete for the act phase of a test: a failed delete is a hard failure, unlike the warn-only ProxyClient.delete_key used at teardown.
tests/e2e/management/management_client.py:211
↓ 9 callersMethoddelete_many
(self, *, where: Mapping[str, object])
tests/unit/repositories/test_chunked_in.py:57
↓ 9 callersFunctiondelete_many_in
( table: DeleteManyTable, field: str, values: Iterable[Hashable], *, atomicity: Atomicity,
litellm/repositories/chunked_in.py:136
↓ 9 callersMethoddelete_team
(self, team_id: str)
tests/e2e/logging/logging_client.py:359
↓ 9 callersMethoddelete_user
(self, user_id: str)
tests/e2e/idp.py:203
↓ 9 callersMethoddeployment_dict
(self, id: str)
litellm/proxy/db/db_spend_update_writer.py:611
↓ 9 callersFunctiondeployment_record
(deployment: &Deployment)
litellm-rust/crates/python-bridge/src/router/host.rs:704
↓ 9 callersFunctiondf
(t)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 9 callersMethoddisarm
(self)
tests/integration/_support/database_relay.py:215
↓ 9 callersMethoddiscovered_model_info
Limits discovered from the provider for a deployment (was ``get_discovered_model_info``).
litellm/router_api.py:415
↓ 9 callersMethoddiscovery_auth_fingerprint
(self)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:19303
↓ 9 callersFunctiondispatchPluginsSync
(s,o,i={})
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 9 callersMethoddownload
(self, path: str, *, headers: BaseModel)
tests/e2e/transport.py:112
↓ 9 callersMethoddrain
(self)
tests/integration/providers/test_vertex_gemini_count_tokens_wire.py:65
↓ 9 callersFunctiondropped_connection_relay
(database_url: str, trigger: bytes)
tests/integration/_support/database_relay.py:376
↓ 9 callersFunctioneB
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 9 callersFunctioneE
(e,t,r)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 9 callersFunctioneR
()
litellm/proxy/_experimental/out/_next/static/chunks/1a2lzi3ursud4.js:1
↓ 9 callersFunctioneV
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 9 callersMethodedit
(self, index: int, suffix: str)
tests/integration/mcp/test_mcp_lifecycle.py:423
↓ 9 callersFunctionef
(e,a)
litellm/proxy/_experimental/out/_next/static/chunks/2r8xiri7nad3g.js:1
↓ 9 callersMethodeffective_oauth2_flow
The oauth2_flow a security decision must use for ``server`` this request. Column-first, shape-fallback: a stamped row returns its explicit va
litellm/proxy/mcp_server/mcp_server_manager.py:1964
↓ 9 callersFunctioneh
litellm/proxy/_experimental/out/_next/static/chunks/2vp9d70y5g3fw.js:1
↓ 9 callersFunctionem
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 9 callersFunctionembed
(gateway: Gateway, model: str, elements: JsonValue, **extra: JsonValue)
tests/integration/providers/test_gemini_embedding_file_block_wire.py:98
↓ 9 callersMethodemit
(&self, event: &PythonCallEvent<'_>)
litellm-rust/crates/host-python/src/driver.rs:74
↓ 9 callersFunctionemptied
(body: Mapping[str, JsonValue], field: str)
tests/integration/caching/response_cache_case.py:247
↓ 9 callersMethodencode
(&self, value: &CacheEntry)
litellm-rust/crates/cache-response/src/codec.rs:12
↓ 9 callersFunctionencode_prompt_id
Convert GitLab path IDs like 'invoice/extract' → 'gitlab::invoice::extract
litellm/integrations/gitlab/gitlab_prompt_manager.py:43
↓ 9 callersFunctionend_user_restricted_registry_cache_key
Cache key for the set of end-user ids whose row carries a restriction auth enforces.
litellm/proxy/common_utils/user_api_key_cache.py:560
↓ 9 callersFunctionendpoint_selection
(call_type: object, module: object = None, model: object = None)
litellm/router_utils/endpoint_eligibility.py:66
↓ 9 callersFunctionendpoint_url
(api_base: str | None, path: str)
litellm/llms/edenai/common_utils.py:77
↓ 9 callersFunctionends_cleanly
(endpoint: Endpoint, raw: str)
tests/integration/providers/_gemini_long_decode_support.py:501
↓ 9 callersFunctionenforce_batch_limits_are_admin_only
Only a proxy admin may change a key or team's batch limits. Every key in ``ADMIN_ONLY_BATCH_LIMIT_METADATA_KEYS`` caps what the holder may do
litellm/proxy/auth/auth_utils.py:1631
↓ 9 callersMethodenqueue_response
(self, response: RecordedResponse)
tests/rust-python-harness/shared/parity/replay.py:41
↓ 9 callersFunctionentry
(value: serde_json::Value)
litellm-rust/crates/cache-azure-blob/tests/cache.rs:48
↓ 9 callersMethodenv
(self)
litellm-rust/crates/redis-resolve/src/keys.rs:59
↓ 9 callersFunctioneo
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 9 callersFunctionepoch_seconds
Seconds since the Unix epoch, on one clock for every host.
litellm-rust/crates/host/src/lifecycle.rs:12
↓ 9 callersFunctionerror_of
(response: httpx.Response)
tests/integration/providers/_vertex_batch_rows.py:120
↓ 9 callersMethodexecute
(&self, operation: Operation, context: Context)
litellm-rust/crates/gateway-mcp/src/native.rs:350
↓ 9 callersFunctionexpected_answers
(row: Row, sents: tuple[Sent, ...])
tests/integration/providers/_idle_upstream_support.py:611
↓ 9 callersMethodextract
(object: Borrowed<'_, '_, PyAny>)
litellm-rust/crates/callbacks-legacy-python/src/logger.rs:43
↓ 9 callersMethodextract
(proxy_request: &Bound<'py, PyAny>)
litellm-rust/crates/python-bridge/src/marshal.rs:152
↓ 9 callersMethodextract_subject_token
The caller's upstream identity token, or ``None`` when the bearer is a LiteLLM key. Validated JWT claims survive virtual-key mapping, so JWT
litellm/proxy/mcp_server/mcp_server_manager.py:4083
↓ 9 callersFunctionextract_text_content
Return the plain-text representation of a message content value.
litellm/llms/oci/chat/cohere.py:79
↓ 9 callersMethodextract_tool_info
Extract name and description from MCP tool or OpenAI function dict.
litellm/proxy/mcp_server/semantic_tool_filter.py:123
↓ 9 callersFunctionf
()
litellm/proxy/_experimental/out/_next/static/chunks/2k-fkubkt19cc.js:26
↓ 9 callersFunctionfake_stream
()
tests/unit/proxy/test_proxy_logging_hook_detection.py:291
↓ 9 callersFunctionfetchMCPServers
( accessToken: string, teamId?: string | null, connectedAppView?: boolean, userId?: string | null, )
ui/litellm-dashboard/src/components/networking.tsx:4468
↓ 9 callersFunctionfindMembership
(userId: string | null)
ui/litellm-dashboard/src/components/team/TeamMemberTab.tsx:88
↓ 9 callersMethodfind_by_name
Find models by name.
litellm/repositories/model_repository.py:91
↓ 9 callersMethodfind_database_service_unavailable_error_in_chain
The exception in the ``__cause__`` / ``__context__`` chain that ``is_database_service_unavailable_error`` accepts, or ``None``. Callers
litellm/proxy/db/exception_handler.py:544
↓ 9 callersFunctionfind_regressions
Return the cells that flipped green→red (``pass`` → ``fail``). A *regression* is defined strictly: a cell that was ``pass`` in ``old_matrix``
tests/e2e/claude_code/matrix_builder.py:201
↓ 9 callersMethodfind_unique
(self, where: Mapping[str, object])
litellm/proxy/policy_engine/policy_registry.py:112
↓ 9 callersMethodfinish
(self)
litellm-rust/crates/python-compat/tests/fixtures.rs:172
↓ 9 callersMethodflush
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 9 callersMethodflush
(&self)
litellm-rust/crates/redis-client/src/batch.rs:87
↓ 9 callersMethodflush_and_get_aggregated_daily_spend_update_transactions
(self)
tests/unit/proxy/db/test_db_spend_update_writer.py:5337
↓ 9 callersFunctionflush_model_usage_transactions
One upsert per rollup row for the whole drained batch, in a single transaction and in key order so concurrent pods take row locks in the same orde
litellm/proxy/db/model_usage_rollup.py:130
↓ 9 callersMethodflush_state_to_db
Drain state aggregator and apply to LiteLLM_AdaptiveRouterState. Returns number of cells flushed.
litellm/router_strategy/adaptive_router/update_queue.py:95
↓ 9 callersMethodfold_reasoning_tokens_into_completion
Reconcile xAI Usage to the OpenAI invariant. xAI accounts ``reasoning_tokens`` separately from ``completion_tokens`` while still summ
litellm/llms/xai/chat/transformation.py:326
↓ 9 callersMethodfor_scenario
(self, identity: str)
tests/integration/compatibility/test_missing_body_param_status.py:652
↓ 9 callersMethodformat_url
Helper function to add query params to the url Args: endpoint: str - the endpoint to add to the url base_targ
litellm/llms/base_llm/passthrough/transformation.py:143
↓ 9 callersFunctiong
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 9 callersFunctiong
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 9 callersFunctiongate
(issue: Pick<IssueForClassification, "title" | "body" | "author_association">)
scripts/classify-issue.ts:146
↓ 9 callersMethodgemini_body
(self)
tests/integration/observability/test_presidio_streaming_output.py:183
↓ 9 callersFunctiongemini_count_contents
( messages: Sequence[Mapping[str, object]], messages_format: TokenCountMessagesFormat, model: str,
litellm/llms/vertex_ai/count_tokens/context.py:203
↓ 9 callersFunctiongemini_model
(scenario: Scenario, url: str, **litellm_params: JsonValue)
tests/integration/providers/test_gemini_embedding_file_block_wire.py:94
↓ 9 callersMethodgemini_path
(self)
tests/integration/observability/test_presidio_streaming_output.py:180
↓ 9 callersMethodgenerate
Generate an API key based on the provided data. Docs: https://docs.litellm.ai/docs/proxy/virtual_keys Args: mod
litellm/proxy/client/keys.py:116
↓ 9 callersFunctiongetCallbacksCall
(accessToken: string, userID: string, userRole: string)
ui/litellm-dashboard/src/components/networking.tsx:2982
↓ 9 callersFunctiongetModelDisplayName
(model: string)
ui/litellm-dashboard/src/components/key_team_helpers/fetch_available_models_team_key.tsx:45
↓ 9 callersMethodget_agent_by_id
Get an agent by its ID from the database
litellm/proxy/agent_endpoints/agent_registry.py:921
← previousnext →8,001–8,100 of 202,479, ranked by callers