MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 8 callersFunctionsummed
(*hops: Hop)
tests/integration/providers/_gemini_long_decode_support.py:74
↓ 8 callersFunctionsynthesize_subtitle_document
Build an SRT/VTT document from OpenAI verbose_json-style word dicts (word/start/end in float seconds, optional speaker). Returns None when th
litellm/litellm_core_utils/audio_utils/subtitle_utils.py:269
↓ 8 callersFunctiont
()
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 8 callersMethodtag
(self, key: str)
tests/e2e/otel_client.py:81
↓ 8 callersMethodtags
(self)
tests/integration/observability/test_langfuse_otel_trace_fields.py:43
↓ 8 callersFunctiontagsControl
(control: MountedFieldControlProps, t: TFunction = i18n.t.bind(i18n))
ui/litellm-dashboard/src/app/(dashboard)/mcp-servers/_components/mcpFieldRules.ts:41
↓ 8 callersFunctionteamDetailHref
(teamId: string)
ui/litellm-dashboard/src/utils/entityLinks.ts:10
↓ 8 callersFunctionteam_admin_may_raise_max_budget
``raise_max_budget`` only takes effect alongside ``max_budget``: a grant to raise a field the team admin may not edit at all is treated as not gra
litellm/proxy/management_endpoints/team_admin_field_permissions.py:288
↓ 8 callersFunctionteam_member_counter
(user_id: str, team_id: str)
litellm/redis/stores/spend_counters/types.py:32
↓ 8 callersFunctionteam_member_me
Get the caller's own team-membership row for the given team. Used by internal users to view their own spend, budget, budget reset date,
litellm/proxy/management_endpoints/team_endpoints.py:5608
↓ 8 callersMethodterminate
(self)
tests/unit/proxy/mcp_server/test_mcp_server_tool_calls_and_headers.py:2649
↓ 8 callersMethodtest_connection
Test the cache connection. Returns: dict: {"status": "success" | "failed", "message": str, "error": Optional[str]}
litellm/caching/base_cache.py:50
↓ 8 callersMethodtext_to_speech_handler
Handles text-to-speech requests. When _is_async=True, returns a coroutine instead of making the call directly.
litellm/llms/custom_httpx/llm_http_handler.py:12604
↓ 8 callersFunctiontierRowById
(rows: readonly T[], id: string | undefined)
ui/litellm-dashboard/src/components/add_model/tier_rows.ts:85
↓ 8 callersFunctiontoDailyData
(response: DailyActivityAggregatedResponse)
ui/litellm-dashboard/src/components/UsagePage/dailyActivityApi.ts:89
↓ 8 callersMethodto_confined
to_real, then resolve symlinks inside the sandbox and refuse anything outside workdir. A repo can contain `link -> ~/.aws/credentials`; witho
litellm/llms/deepagents/harness/sandbox_backend.py:143
↓ 8 callersFunctionto_pyerr
(error: Error)
litellm-rust/crates/python-bridge/src/routes/ocr/errors.rs:14
↓ 8 callersMethodtool_schema
(self)
litellm/llms/anthropic/chat/transformation.py:3469
↓ 8 callersFunctiontq
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 8 callersFunctiontranscribe_storage_refusal
Transcribe reads the media and writes the transcript with the proxy's own AWS credentials, so a non-admin key may only point a job at buckets
litellm/proxy/pass_through_endpoints/llm_provider_handlers/transcribe_passthrough_logging_handler.py:259
↓ 8 callersMethodtransform
(self, payload: str)
litellm/llms/soniox/realtime/transformation.py:281
↓ 8 callersMethodtransform_decisions_response
( self, model: str, custom_llm_provider: str, raw_response: httpx.Response,
litellm/llms/base_llm/decisions/transformation.py:682
↓ 8 callersMethodtransform_image_edit_response
( self, model: str, raw_response: httpx.Response, logging_obj: LiteLLMLoggingO
litellm/llms/bedrock/image_edit/amazon_nova_canvas_image_edit_transformation.py:399
↓ 8 callersFunctiontransform_messages_request
( request: MessagesRequest, context: &MessagesTransformContext, )
litellm-rust/crates/llms/src/anthropic/messages/transformation.rs:121
↓ 8 callersMethodtransform_request
( self, model: str, messages: list[AllMessageValues], optional_params: dict,
litellm/llms/fireworks_ai/chat/transformation.py:672
↓ 8 callersMethodtransform_request
Transform the overall request to be sent to the API. Returns: dict: The transformed request. Sent as the body of the API
litellm/llms/openrouter/chat/transformation.py:146
↓ 8 callersFunctiontransform_response
(body: Value)
litellm-rust/crates/llms/src/bedrock/chat/converse_transformation.rs:391
↓ 8 callersFunctiontransform_response
(body: Value)
litellm-rust/crates/llms/src/anthropic/chat/transformation.rs:289
↓ 8 callersMethodtransform_response
( self, model: str, raw_response: httpx.Response, model_response: ModelRespons
litellm/llms/oci/chat/transformation.py:719
↓ 8 callersMethodtransform_response
( self, model: str, raw_response: httpx.Response, model_response: ModelRespons
litellm/llms/openai/openai.py:312
↓ 8 callersMethodtranslate_anthropic_output_format_to_openai
Translate Anthropic's output_format to OpenAI's response_format. Anthropic output_format: {"type": "json_schema", "schema": {...}}
litellm/llms/anthropic/messages/adapters/transformation.py:997
↓ 8 callersFunctiontruncate_base64_in_messages_async
Same result as truncate_base64_in_messages, but payloads whose string content reaches BASE64_TRUNCATION_OFFLOAD_THRESHOLD_CHARS are copied in
litellm/litellm_core_utils/logging_utils.py:176
↓ 8 callersFunctiontunnelling_forward_proxy
(destination_port: int, port: int = 0)
tests/integration/_support/forward_proxy.py:85
↓ 8 callersMethodtx
(self, *, timeout: timedelta)
litellm/proxy/db/baseline_accounting.py:196
↓ 8 callersFunctionty
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 8 callersFunctionunavailable
(kind: str = "transport")
tests/unit/redis/stores/spend_counters_double.py:29
↓ 8 callersMethoduncached_price
(self, result: object)
litellm/litellm_core_utils/litellm_logging.py:2333
↓ 8 callersFunctionunconvertible_anthropic_blocks
(messages: Sequence[Mapping[str, object]])
litellm/llms/anthropic/messages/convertible_blocks.py:92
↓ 8 callersMethodupdate
(self, where: Mapping[str, object], data: Mapping[str, object])
tests/unit/proxy/db/test_object_permission_repository.py:20
↓ 8 callersFunctionupdate_batch_in_database
Update batch status and object in ManagedObjectTable. Args: batch_id: The batch ID (unified/encoded) unified_batch_id: Resul
litellm/proxy/openai_files_endpoints/common_utils.py:1646
↓ 8 callersMethodupdate_end_user_spend
( n_retry_times: int, prisma_client: PrismaClient, proxy_logging_obj: ProxyLogging,
litellm/proxy/utils.py:8673
↓ 8 callersMethodupdate_in_memory_litellm_params
The base implementation blindly ``setattr``s every field on ``litellm_params`` (including ``on_flagged``/``advisory_system_message``/
litellm/proxy/guardrails/guardrail_hooks/lakera_ai_v2.py:309
↓ 8 callersMethodupdate_many
(self, *, where: Mapping[str, object], data: Mapping[str, object])
litellm/repositories/prisma_protocols.py:140
↓ 8 callersFunctionupstream
()
tests/unit/proxy/proxy_server/test_streaming_helpers.py:145
↓ 8 callersFunctionupstream
Starts an upstream that answers its n-th request with the n-th response and 404s after.
litellm-rust/crates/inference-transcription/tests/support/mod.rs:25
↓ 8 callersFunctionuse
(...e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 8 callersFunctionuseCurrentUser
()
ui/litellm-dashboard/src/app/(dashboard)/hooks/users/useCurrentUser.ts:8
↓ 8 callersFunctionuseModelCostMap
(enabled = true, catalogOnly = false)
ui/litellm-dashboard/src/app/(dashboard)/hooks/models/useModelCostMap.ts:7
↓ 8 callersFunctionuseTheme
()
ui/litellm-dashboard/src/contexts/ThemeContext.tsx:39
↓ 8 callersFunctionuseUrlTableState
(options: UrlTableStateOptions<F>)
ui/litellm-dashboard/src/components/shared/DataTable/useUrlTableState.ts:127
↓ 8 callersFunctionuser_counter
(user_id: str)
litellm/redis/stores/spend_counters/types.py:36
↓ 8 callersFunctionuser_has_admin_privileges
Check if user has admin privileges (proxy admin, team admin, or org admin). Args: user_api_key_dict: User API key authentication obj
litellm/proxy/management_endpoints/common_utils.py:318
↓ 8 callersFunctionuser_transcript
The USER ASR transcript block Bedrock emits once it has consumed the user turn.
tests/integration/_support/bedrock_realtime_peer.py:65
↓ 8 callersFunctionv
()
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:1
↓ 8 callersFunctionv
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 8 callersFunctionvalidate_and_fix_thinking_param
Coerces bool thinking values (True becomes enabled with the default medium budget, False becomes None) and normalizes camelCase keys in the t
litellm/utils.py:9670
↓ 8 callersFunctionvalidate_deployment_max_agentic_loops
Reject a per-deployment `max_agentic_loops` the agentic loop cannot honor. Checked here rather than on `LiteLLM_Params` because the proxy bu
litellm/proxy/proxy_server.py:5502
↓ 8 callersFunctionvalidate_environment
Checks if the environment variables are valid for the given model. Args: model (Optional[str]): The name of the model. Defaults to N
litellm/utils.py:8065
↓ 8 callersMethodvalidate_environment
Validate environment and set up Azure authentication headers. Azure supports: 1. API key via 'api-key' header 2. Azur
litellm/llms/azure_ai/anthropic/transformation.py:56
↓ 8 callersMethodvalidate_environment
( &self, headers: Vec<(String, String)>, api_key: Option<&str>, config: &Verte
litellm-rust/crates/auth-gcp/src/auth.rs:39
↓ 8 callersFunctionvalidate_upload
( *, content: bytes, scanner: MalwareScanner, max_size_bytes: int = MAX_UPLOAD_SIZE_BYTES, )
litellm/proxy/rag_endpoints/upload_security.py:247
↓ 8 callersMethodverify
( &'a self, credential: &'a litellm_gateway_auth::Credential, _: &'a axum::http::reque
litellm-rust/crates/gateway-auth/tests/auth.rs:127
↓ 8 callersFunctionverify_org_access
Verify the caller is either a proxy admin or an org admin of the given organization. Raises HTTPException(403) if the caller does not have a
litellm/proxy/management_endpoints/organization_endpoints.py:269
↓ 8 callersFunctionvideo_generation_cost
Calculates the cost for video generation based on duration in seconds. Input: - model: str, the model name without provider prefix
litellm/llms/openai/cost_calculation.py:131
↓ 8 callersFunctionvideo_model_group
The group a video id names. A provider model that several groups share resolves to the group of the deployment that created the video, under
litellm/proxy/video_endpoints/utils.py:100
↓ 8 callersMethodwait
(self)
tests/unit/llms/opencode/harness/test_transformation.py:97
↓ 8 callersMethodwarnings
(self)
tests/unit/proxy/health_endpoints/test_deployment_warning_endpoints.py:96
↓ 8 callersFunctionwire_parts
(wire: Wire)
tests/integration/providers/test_gemini_embedding_file_block_wire.py:80
↓ 8 callersFunctionwired_provider
The operator's provider: one owned exporter plus the tenant fan-out.
tests/unit/integrations/otel/test_otel_v2_destinations.py:129
↓ 8 callersFunctionwith_answered_status
(exc: Exception)
litellm/proxy/anthropic_endpoints/answered_status.py:51
↓ 8 callersMethodwith_before_send
( self, before_provider_request: impl Fn(WireRequest, &RequestContext) -> Result<WireRequest,
litellm-rust/crates/inference-ocr/tests/ocr/main.rs:181
↓ 8 callersMethodwith_config
(self, config: ResponseCacheConfig)
litellm-rust/crates/cache-response/src/response.rs:70
↓ 8 callersFunctionwith_ptu_consumption
``activity`` with PTU-hours attached from the deployments ``team_id`` is served from (every sized deployment when the page spans teams), untouched
litellm/proxy/management_endpoints/ptu_consumption.py:138
↓ 8 callersMethodwithout_rejected
(self, errors: &[Error])
litellm-rust/crates/model-catalog/src/catalog.rs:341
↓ 8 callersFunctionwithout_retries
()
tests/e2e/e2e_http.py:301
↓ 8 callersFunctionwrap_table_actions_for_config_sync
( actions: "TableActions[RowT_co]", table_name: str, publish: PublishConfigChange = publish_config
litellm/proxy/common_utils/config_sync_pubsub.py:214
↓ 8 callersMethodwrite
Replace the named indexes in router-core, then read them back.
litellm/router_rust/surface/indexes.py:434
↓ 8 callersMethodwrite
(self, batch: LiteLLMBatch, age: timedelta = timedelta(0))
tests/unit/proxy/batches_endpoints/test_litellm_executed_batches.py:176
↓ 8 callersMethodwrite
Apply a host write.
litellm-rust/crates/router-core/src/host_index.rs:71
↓ 8 callersFunctionx
(e,t,n,r,a,l,u,o)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 7 callersFunction$
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 7 callersFunctionB
(e,t,n,r,a,l,u,o,i,c)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 7 callersFunctionE
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 7 callersFunctionG
()
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 7 callersMethodGetKey
(keyID string)
terraform/provider/litellm/client.go:75
↓ 7 callersFunctionI
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 7 callersFunctionK
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 7 callersFunctionLf
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 7 callersFunctionP
(t)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 7 callersMethodPATCH
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 7 callersFunctionQr
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 7 callersFunctionS
(e,t,n,r,a,s,f,d,h,p,g,S,R)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 7 callersFunctionS
(e,s,a)
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:1
↓ 7 callersFunctionSa
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 7 callersFunctionSet
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 7 callersFunctionSf
(t,e,r)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 7 callersFunctionTf
(t)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 7 callersFunctionV
({approvalStatus:e,onApprove:t,onReject:r})
litellm/proxy/_experimental/out/_next/static/chunks/2k-fkubkt19cc.js:1
↓ 7 callersFunctionV
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 7 callersFunctionVb
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
← previousnext →9,701–9,800 of 202,479, ranked by callers