Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/BerriAI/litellm
/ functions
Functions
202,479 in github.com/BerriAI/litellm
⨍
Functions
202,479
◇
Types & classes
26,341
↳
Endpoints
5,595
↓ 5 callers
Function
io_token_refund_failure
( dual_cache: DualCache, kwargs: Mapping[str, object] | None, *, any_attempt: bool = False, )
litellm/router_utils/pre_call_checks/io_token_rate_limit_check.py:905
↓ 5 callers
Function
is
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callers
Function
isAgentEndpoint
(endpointId: EndpointIdType)
ui/litellm-dashboard/src/app/(dashboard)/playground/components/compareUI/endpoint_config.ts:69
↓ 5 callers
Function
isBuiltInTierName
(name: string)
ui/litellm-dashboard/src/components/add_model/tier_rows.ts:53
↓ 5 callers
Function
isCurrent
(run: object)
ui/litellm-dashboard/src/components/team/useMemberBudgetReset.ts:34
↓ 5 callers
Method
isFrozen
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callers
Function
isHeldOAuthTokenStale
( values: Record<string, unknown>, authorizedIdentity: string | undefined, )
ui/litellm-dashboard/src/components/mcp_tools/types.tsx:232
↓ 5 callers
Function
isImmutable
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callers
Function
isRecord
(value: unknown)
vscode-extension/src/messages.ts:48
↓ 5 callers
Method
is_anthropic_usage_object
Anthropic reports prompt cache tokens as top-level ``cache_read_input_tokens`` / ``cache_creation_input_tokens``; no other API surface uses th
litellm/llms/anthropic/chat/transformation.py:2943
↓ 5 callers
Method
is_azure_content_policy_violation_error
Check if an error string indicates a content policy violation error.
litellm/litellm_core_utils/exception_mapping_utils.py:130
↓ 5 callers
Function
is_azure_model_router_request
Check if a request went down the Azure Model Router route. ``model`` here is what the *client* sent, a model group alias with no ``model_rou
litellm/proxy/common_request_processing.py:1768
↓ 5 callers
Method
is_builtin_eu_jev_decision_route
(route: str)
litellm/proxy/auth/route_checks.py:526
↓ 5 callers
Function
is_caller_timeout_408
A 408 that arrives before the caller-set timeout could have fired came from the provider. ``ended`` overrides ``model_call_details["end_time"]``
litellm/router_utils/cooldown_handlers.py:838
↓ 5 callers
Function
is_chat
(request: Request)
tests/integration/streaming/test_mid_stream_fallback_continuation.py:122
↓ 5 callers
Method
is_claimed
(self, interaction_id: str)
litellm/interactions/background_cost_polling.py:119
↓ 5 callers
Function
is_codex_user_agent
(user_agent: str)
litellm/litellm_core_utils/core_helpers.py:36
↓ 5 callers
Method
is_connect
(&self)
litellm-rust/crates/http/src/error.rs:381
↓ 5 callers
Function
is_custom_tool_call
Check if a tool call name corresponds to a custom tool.
litellm/responses/litellm_completion_transformation/custom_tools.py:82
↓ 5 callers
Method
is_error
(self)
litellm/proxy/mcp_server/outbound_credentials/result.py:39
↓ 5 callers
Function
is_guardrail_intervention
Returns True if the exception represents an intentional guardrail block (this was logged previously as an API failure - guardrail_failed_to_r
litellm/integrations/custom_guardrail.py:93
↓ 5 callers
Method
is_input_examples_used
Check if input_examples is being used in any tools. Returns True if any tool has input_examples field.
litellm/llms/anthropic/common_utils.py:868
↓ 5 callers
Function
is_json_content_type
True iff the body should be parsed as JSON.
litellm/proxy/common_utils/http_parsing_utils.py:115
↓ 5 callers
Function
is_legacy_upstream_delegate
True for an interactive ``auth_type=oauth2`` server with ``delegate_auth_to_upstream=true``, whose caller ``Authorization`` is the upstream token.
litellm/proxy/mcp_server/mcp_server_manager.py:1569
↓ 5 callers
Function
is_litellm_executed_batch
(decoded_unified_batch_id: str)
litellm/proxy/openai_files_endpoints/common_utils.py:230
↓ 5 callers
Function
is_litellm_owned_kwarg
(name: str)
litellm/types/utils.py:4575
↓ 5 callers
Method
is_live
(self, token: str)
tests/integration/_support/oauth_server.py:46
↓ 5 callers
Method
is_lock_timeout_error
True iff Postgres cancelled a statement for exceeding ``lock_timeout`` (SQLSTATE 55P03). The statement never acquired its lock, so it never
litellm/proxy/db/exception_handler.py:361
↓ 5 callers
Method
is_mai_model
(model: str)
litellm/llms/azure_ai/image_generation/mai_transformation.py:142
↓ 5 callers
Function
is_managed
Return ``True`` iff *value* decodes to a passthrough managed ID.
litellm/proxy/pass_through_endpoints/managed_id_codec.py:90
↓ 5 callers
Function
is_message_stop_chunk
(chunk: object)
litellm/llms/anthropic/messages/native/streaming_iterator.py:44
↓ 5 callers
Method
is_mid_conversation_tool_change_used
(self, messages: Sequence[object])
litellm/llms/anthropic/common_utils.py:771
↓ 5 callers
Method
is_multimodal_embeddings
(model: str)
litellm/llms/voyage/embedding/transformation_multimodal.py:51
↓ 5 callers
Function
is_nested_path
Check if path requires nested handling. Returns True if path contains '.' or '[' (array notation).
litellm/litellm_core_utils/dot_notation_indexing.py:236
↓ 5 callers
Method
is_o_series_model
(self, model: str)
litellm/llms/azure/chat/o_series_transformation.py:100
↓ 5 callers
Function
is_oauth_credential_expired
Return True if the OAuth2 credential's access_token has expired. Checks the ``expires_at`` ISO-format string stored in the credential payload.
litellm/proxy/mcp_server/db.py:1857
↓ 5 callers
Function
is_openai_backed_api_base
(api_base: str)
litellm/llms/openai/common_utils.py:146
↓ 5 callers
Method
is_openai_catalog_model
(model: str)
litellm/llms/openai/chat/gpt_transformation.py:279
↓ 5 callers
Method
is_openai_chat_completions_route
Check if the URL route is an OpenAI chat completions endpoint.
litellm/proxy/pass_through_endpoints/llm_provider_handlers/openai_passthrough_logging_handler.py:231
↓ 5 callers
Method
is_overflow
(self)
tests/integration/_support/prometheus_series.py:110
↓ 5 callers
Function
is_passthrough_request_using_router_model
Returns True if the model is in the llm_router model names
litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:215
↓ 5 callers
Method
is_prisma_engine_internal_error
True iff ``e`` is a non-``PrismaError`` exception raised from inside prisma-client-py's query-engine layer. During the instant a DB c
litellm/proxy/db/exception_handler.py:413
↓ 5 callers
Method
is_programmatic_tool_calling_used
Check if programmatic tool calling is being used (tools with allowed_callers field). Returns True if any tool has allowed_callers co
litellm/llms/anthropic/common_utils.py:842
↓ 5 callers
Function
is_rate_limit_shaped
Classify an outcome as a retryable rate-limit-shaped failure. A `ClaudeCLIError` matches on its message (which is where the driver's own time
tests/e2e/claude_code/cli_driver.py:318
↓ 5 callers
Function
is_raw_sse_stream
(all_chunks: Sequence[object])
litellm/llms/anthropic/messages/stream_assembly.py:452
↓ 5 callers
Function
is_reasoning_auto_summary_enabled
Check whether the default 'summary: detailed' injection is enabled (opt-in).
litellm/llms/anthropic/messages/utils.py:187
↓ 5 callers
Function
is_refresh_envelope
Cheap prefix check for a REFRESH envelope so the token endpoint can route a refresh grant that carries an envelope vs a raw upstream refresh token
litellm/proxy/mcp_server/outbound_credentials/envelope.py:305
↓ 5 callers
Function
is_registered_custom_provider
(custom_llm_provider: str | None)
litellm/litellm_core_utils/get_llm_provider_logic.py:610
↓ 5 callers
Function
is_retryable_shaped
Either retryable shape. This, not `is_rate_limit_shaped`, is what the retry loop asks: both shapes clear on their own given time.
tests/e2e/claude_code/cli_driver.py:336
↓ 5 callers
Function
is_sensitive_callback_key
Return ``True`` if ``key`` is present in ``extra`` (checked as-is), or if its lowercase form is in ``_EXTRA_SENSITIVE_CALLBACK_KEYS``, or if `
litellm/proxy/common_utils/callback_utils.py:754
↓ 5 callers
Function
is_short_mcp_tool_prefix_enabled
Return True when the short-ID tool prefix mode is enabled. Read at call time (not import time) so tests and runtime config changes take effec
litellm/proxy/mcp_server/utils.py:111
↓ 5 callers
Function
is_streaming_request_fn
(request: Request)
litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:1070
↓ 5 callers
Method
is_thinking_enabled
(self, non_default_params: dict)
litellm/llms/base_llm/chat/transformation.py:128
↓ 5 callers
Method
is_tinyfish_route
(self, url_route: str, custom_llm_provider: str | None)
litellm/proxy/pass_through_endpoints/success_handler.py:635
↓ 5 callers
Function
is_undiscoverable_deployment
(deployment: Mapping[str, object])
litellm/proxy/common_utils/discoverable_model_filter.py:19
↓ 5 callers
Function
is_unique_violation
(exc: BaseException)
litellm/repositories/base_repository.py:131
↓ 5 callers
Function
is_valid_deployment_tag
Check if a tag is valid, the matching can be either any or all based on `match_any` flag
litellm/router_strategy/tag_based_routing.py:119
↓ 5 callers
Function
is_video_status_call_type
(call_type: object)
litellm/types/videos/utils.py:37
↓ 5 callers
Function
it
(t)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 5 callers
Function
iter_client_callback_metadata_dicts
( kwargs: Mapping[str, object], )
litellm/litellm_core_utils/initialize_dynamic_callback_params.py:30
↓ 5 callers
Function
j
()
litellm/proxy/_experimental/out/_next/static/chunks/11et800l-khs-.js:49
↓ 5 callers
Function
j
litellm/proxy/_experimental/out/_next/static/chunks/2j96ftcthirif.js:141
↓ 5 callers
Function
job_charged_once_marker_key
(spend_key: str, job: ChargeOnceJob)
litellm/litellm_core_utils/batch_utils.py:310
↓ 5 callers
Method
json
(self)
litellm/llms/edenai/embedding/transformation.py:28
↓ 5 callers
Method
json
(self)
litellm/llms/watsonx/embed/transformation.py:34
↓ 5 callers
Method
json
(self)
litellm/llms/lemonade/chat/transformation.py:34
↓ 5 callers
Method
json
(self)
tests/unit/llms/openai/responses/test_openai_responses_transformation.py:3414
↓ 5 callers
Function
json_body
(mapping: Mapping[str, object])
litellm/llms/sail/common_utils.py:47
↓ 5 callers
Function
json_object
(payload: str, error: ProtocolErrorType = RealtimeTranscriptionProtocolError)
litellm/llms/base_llm/realtime/transcription_protocol.py:65
↓ 5 callers
Function
json_or_none
JSON-serialize ``value`` (falling back to ``str``); ``None`` on failure.
litellm/integrations/otel/mappers/utils.py:102
↓ 5 callers
Function
judge_acompletion
Dispatch a judge call through the proxy's router when the judge model is a configured deployment (DB-stored credentials work), through the SDK for
litellm/litellm_core_utils/llm_judge.py:174
↓ 5 callers
Function
junit_properties
The stall table as `perf_event_loop_*` properties for the dashboard: every hold over the threshold with the allowlist's total as its limit, the ho
tests/e2e/perf/setup/event_loop.py:235
↓ 5 callers
Function
jwks_unavailable_exception
(error: JWKSUnreachableError)
litellm/proxy/auth/handle_jwt.py:221
↓ 5 callers
Function
k
litellm/proxy/_experimental/out/_next/static/chunks/1d5pm_8gbmvlm.js:1
↓ 5 callers
Function
k
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 5 callers
Function
k
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:8
↓ 5 callers
Function
keyDetailHref
(keyToken: string)
ui/litellm-dashboard/src/utils/entityLinks.ts:15
↓ 5 callers
Function
keyRawConfig
(t *testing.T, routes []string)
terraform/provider/litellm/resource_key_test.go:335
↓ 5 callers
Method
key_alias_count
(self, key_alias: str)
tests/e2e/management/management_client.py:294
↓ 5 callers
Function
key_and_team_logging_fields
(user_api_key_dict: UserAPIKeyAuth, proxy_config: ProxyConfig)
litellm/proxy/litellm_pre_call_utils.py:1343
↓ 5 callers
Method
key_page
(self, scope: DailyActivityScope, *, offset: int, limit: int)
litellm/repositories/daily_activity_repository.py:208
↓ 5 callers
Function
key_window_counter
(token: str, budget_duration: str)
litellm/redis/stores/spend_counters/types.py:20
↓ 5 callers
Function
keycloak_from_env
()
tests/e2e/idp.py:352
↓ 5 callers
Function
keys_of
(team: str)
tests/integration/_support/scim.py:144
↓ 5 callers
Function
ko
(t,e)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 5 callers
Function
l
()
litellm/proxy/_experimental/out/_next/static/chunks/1d5pm_8gbmvlm.js:1
↓ 5 callers
Function
l
(e,t,i)
litellm/proxy/_experimental/out/_next/static/chunks/1l-5fdzkk72ex.js:1
↓ 5 callers
Function
lG
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 5 callers
Function
lX
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 5 callers
Function
la
(e,t,n,r)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 5 callers
Function
landed
(key: str, marker: str)
tests/integration/authorization/_hidden_alias_budget.py:250
↓ 5 callers
Function
langfuse_control
(secret: Canary)
tests/integration/security/test_callback_credentials.py:130
↓ 5 callers
Function
lastSegment
(path: string)
ui/litellm-dashboard/src/components/claude_code_plugins/helpers.ts:80
↓ 5 callers
Function
last_json_object
The last top-level `{...}` in text that parses as a JSON object, re-serialized.
litellm/llms/base_llm/harness/utils.py:48
↓ 5 callers
Function
latest_transcript_model
(transcript_path: str)
litellm/proxy/client/cli/commands/statusline_script.py:168
↓ 5 callers
Function
ledger
Every migration in the ledger that was not rolled back, mapped to whether it finished.
tests/integration/database/test_request_log_indexes_at_boot.py:193
↓ 5 callers
Function
lg
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 5 callers
Function
license_expiry_condition
(expiration_date: str | None, now: datetime)
litellm/proxy/health_endpoints/deployment_warning_endpoints.py:118
↓ 5 callers
Function
list
(...s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callers
Method
list
(self, context: OperationContext, request: CatalogListRequest)
litellm/proxy/mcp_server/server_resolution.py:142
← previous
next →
16,101–16,200 of 202,479, ranked by callers