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
↓ 7 callers
Function
getHeuristicV2SuccessThresholdError
( threshold: number | undefined, t: TFunction = i18n.t.bind(i18n), )
ui/litellm-dashboard/src/components/add_model/build_complexity_router_config.ts:400
↓ 7 callers
Function
get_access_object
- Check if access_group_id in proxy AccessGroupTable - Checks cache first unless authoritative writer admission is requested - if valid,
litellm/proxy/auth/auth_checks.py:3805
↓ 7 callers
Method
get_added_tokens_decoder
(self)
litellm/litellm_core_utils/tokenizer.py:423
↓ 7 callers
Method
get_additional_headers
( additiona_headers: dict | None, )
litellm/litellm_core_utils/litellm_logging.py:7284
↓ 7 callers
Function
get_admin_mcp_permissions
( auth: UserAPIKeyAuth, request: Request, tool: str | None = None, path: str | None = None )
litellm/proxy/admin_mcp.py:118
↓ 7 callers
Function
get_all_bedrock_regions
Get all Bedrock regions, cached at module level.
litellm/llms/bedrock/common_utils.py:1176
↓ 7 callers
Method
get_api_base
(api_base: str | None = None)
litellm/llms/azure_ai/common_utils.py:287
↓ 7 callers
Function
get_audio_file_name
Safely get the name of a file-like object or return its string representation. Args: file_obj (Any): A file-like object or any other
litellm/litellm_core_utils/audio_utils/utils.py:174
↓ 7 callers
Method
get_auth_token
Get auth token from ANTHROPIC_AUTH_TOKEN env var. Unlike api_key (which uses X-Api-Key header), auth_token uses Authorization: Bearer
litellm/llms/anthropic/common_utils.py:1690
↓ 7 callers
Method
get_available_guardrail
(self, guardrail_name: str)
litellm/router_deprecated.py:662
↓ 7 callers
Function
get_azure_ad_token_from_oidc
Get Azure AD token from OIDC token Args: azure_ad_token: str azure_client_id: Optional[str] azure_tenant_id: Optiona
litellm/llms/azure/common_utils.py:476
↓ 7 callers
Function
get_bedrock_response_stream_shape
Lazily load and cache the bedrock-runtime ResponseStream shape for the process. Avoids importing botocore (and logging warnings) unless Bedr
litellm/llms/bedrock/common_utils.py:2385
↓ 7 callers
Function
get_bigmodel_url
(api_base: str | None, endpoint: Literal["chat", "responses", "messages"])
litellm/llms/bigmodel/common_utils.py:44
↓ 7 callers
Function
get_blog_posts
Public entry point, returns the blog posts.
litellm/litellm_core_utils/get_blog_posts.py:160
↓ 7 callers
Function
get_budget_window_start
Start of the budget period that ends at `reset_at`, under the same rules `get_next_standardized_reset_time` used to pick it: `30d` and `Nmo` span
litellm/litellm_core_utils/duration_parser.py:170
↓ 7 callers
Method
get_cache
( self, key: str, local_only: bool = False, **kwargs: object, )
litellm/proxy/utils.py:586
↓ 7 callers
Method
get_cache
(self, key: str)
litellm/llms/databricks/common_utils.py:34
↓ 7 callers
Method
get_callback_env_vars
Return the environment variables associated with a given callback name as defined in the proxy callback registry. Args:
litellm/integrations/custom_logger.py:104
↓ 7 callers
Method
get_chat_completion_prompt
Apply cache control directives based on specified injection points. Returns: - model: str - the model to use - messa
litellm/integrations/anthropic_cache_control_hook.py:825
↓ 7 callers
Method
get_complete_file_url
( self, api_base: str | None, api_key: str | None, model: str, optiona
litellm/llms/base_llm/files/transformation.py:94
↓ 7 callers
Method
get_complete_url
Get the Base endpoint for Vertex AI Search API. Branches on whether a `vertex_engine_id` is configured: - Engine ID present:
litellm/llms/vertex_ai/vector_stores/search_api/transformation.py:330
↓ 7 callers
Method
get_complete_url
( self, api_base: str | None, api_key: str | None, model: str, optiona
litellm/llms/cloudflare/chat/transformation.py:31
↓ 7 callers
Function
get_container_forwarding_params
( container_id: str, original_container_id: str, custom_llm_provider: str )
litellm/proxy/container_endpoints/ownership.py:79
↓ 7 callers
Method
get_cost_for_code_interpreter
Calculate cost for code interpreter feature. Azure: $0.03 USD per session (from model cost map) OpenAI: $0.03 USD per sessio
litellm/litellm_core_utils/llm_cost_calc/tool_call_cost_tracking.py:832
↓ 7 callers
Function
get_current_env_values
Read current env var values as fallback when no DB record exists.
litellm/proxy/management_endpoints/config_override_endpoints.py:194
↓ 7 callers
Function
get_custom_labels_from_tags
Get custom labels from tags based on admin configuration. Supports both exact matches and wildcard patterns: - Exact match: "prod" match
litellm/integrations/prometheus.py:5224
↓ 7 callers
Function
get_customer_user_header_from_mapping
Return the header_name mapped to CUSTOMER role, if any (dict-based).
litellm/proxy/auth/auth_utils.py:1912
↓ 7 callers
Method
get_datadog_logger_for_request
Get a team-scoped DataDogLogger for a given request. Resolves and caches per-team DataDogLogger instances using DynamicLoggingCache,
litellm/integrations/datadog/datadog_team_handler.py:30
↓ 7 callers
Method
get_end_user_id
(self, token: dict, default_value: str | None)
litellm/proxy/auth/handle_jwt.py:471
↓ 7 callers
Function
get_file_content_as_dictionary
Get the file content as a list of dictionaries from JSON Lines format, skipping malformed lines
litellm/batches/batch_utils.py:669
↓ 7 callers
Method
get_gcs_logging_config
Returns the bucket and service account this logger was configured with.
litellm/integrations/gcs_bucket/gcs_bucket_base.py:141
↓ 7 callers
Function
get_image
Get logo to show on admin UI
litellm/proxy/proxy_server.py:20107
↓ 7 callers
Function
get_jwt_key_mapping_cache_keys_for_tokens
Cache keys of every JWT claim mapped to any of the given virtual keys.
litellm/proxy/auth/auth_checks.py:4305
↓ 7 callers
Function
get_kubernetes_pods
( model_id: str, user_api_key_dict: Annotated[UserAPIKeyAuth, Depends(user_api_key_auth)], )
litellm/proxy/management_endpoints/model_management_endpoints.py:1612
↓ 7 callers
Method
get_langfuse_logger_for_request
This function is used to get the LangFuseLogger for a given request 1. If dynamic credentials are passed - check if a La
litellm/integrations/langfuse/langfuse_handler.py:24
↓ 7 callers
Method
get_langfuse_otel_config
Retrieves the Langfuse OpenTelemetry configuration based on environment variables. Environment Variables: LANGFUSE_PUBLI
litellm/integrations/langfuse/langfuse_otel.py:421
↓ 7 callers
Function
get_litellm_gateway_api_key
Get the stored CLI API key for use with LiteLLM SDK. This function reads the credential created by `lite login` and returns the API key
litellm/litellm_core_utils/cli_token_utils.py:409
↓ 7 callers
Function
get_litellm_web_search_tool
Get the standard LiteLLM web search tool definition. This is the canonical tool definition that all native web search tools (like Anthro
litellm/integrations/websearch_interception/tools.py:69
↓ 7 callers
Function
get_llm_router
The proxy's router, or None outside a running proxy. Injected rather than imported where it is used, so the savings computation stays a pure
litellm/proxy/db/db_spend_update_writer.py:596
↓ 7 callers
Method
get_members_with_roles_locked
Return the team's members_with_roles. The caller must already hold ``TEAM_ADVISORY_LOCK_SQL`` for this team_id on ``tx`` before calling this.
litellm/repositories/team_repository.py:130
↓ 7 callers
Method
get_metadata
(self, name: str)
litellm/models/plugin_upload.py:166
↓ 7 callers
Function
get_model_group_info
( llm_router: Router, all_models_str: Sequence[str], model_group: str | None, team_id: str | None = None )
litellm/proxy/proxy_server.py:18796
↓ 7 callers
Method
get_model_names
(self)
tests/unit/llms/anthropic/messages/test_safeguards.py:341
↓ 7 callers
Method
get_model_response_iterator
(self, streaming_response, sync_stream, json_mode=False)
tests/unit/llms/custom_httpx/test_llm_http_handler.py:4891
↓ 7 callers
Function
get_models_from_unified_file_id
Extract model names from unified file ID. Example: unified_file_id = "litellm_proxy:application/octet-stream;unified_id,c4843482-b176-49
litellm/proxy/openai_files_endpoints/common_utils.py:181
↓ 7 callers
Method
get_openai_compatible_provider_info
( self, api_base: str | None, api_key: str | None, )
litellm/llms/lemonade/chat/transformation.py:236
↓ 7 callers
Method
get_optional_params_responses_api
Get optional parameters for the responses API. Args: params: Dictionary of all parameters model: The model n
litellm/responses/utils.py:293
↓ 7 callers
Function
get_or_create_hidden_params
(obj: object)
litellm/litellm_core_utils/hidden_params.py:160
↓ 7 callers
Method
get_output_str_from_response
(self, response_obj: object, kwargs: Mapping[str, object])
litellm/integrations/galileo.py:638
↓ 7 callers
Method
get_permissions_for_team_member
Returns the permissions for a team member. - If team has explicit permissions set (including []), use those plus baseline
litellm/proxy/management_helpers/team_member_permission_checks.py:28
↓ 7 callers
Function
get_prisma_client
Get the prisma client from proxy_server.
litellm/proxy/anthropic_endpoints/claude_code_endpoints/claude_code_marketplace.py:122
↓ 7 callers
Method
get_provider_files_config
( model: str, provider: LlmProviders, )
litellm/utils.py:10965
↓ 7 callers
Function
get_provider_interactions_api_config
Get the interactions API config for the given provider. Args: provider: The LLM provider name model: Optional model name
litellm/interactions/utils.py:28
↓ 7 callers
Function
get_provider_specific_params
Get provider-specific parameters for different guardrail types. Returns a dictionary mapping guardrail providers to their specific parameter
litellm/proxy/guardrails/guardrail_endpoints.py:2031
↓ 7 callers
Method
get_provider_vector_store_files_config
( provider: LlmProviders, )
litellm/utils.py:11133
↓ 7 callers
Method
get_retrieve_batch_url
Get the complete URL for batch retrieval request. Args: api_base: Base API URL (optional, will use default if not provid
litellm/llms/anthropic/batches/transformation.py:140
↓ 7 callers
Function
get_router_metadata_variable_name
Helper to return what the "metadata" field should be called in the request data For all /thread or /assistant endpoints we need to call this
litellm/litellm_core_utils/batch_utils.py:259
↓ 7 callers
Function
get_scope_response
()
litellm/proxy/mcp_server/legacy_callbacks.py:111
↓ 7 callers
Function
get_secret_from_manager
Get a secret from the configured secret manager. Args: client: The secret manager client instance key_manager: The type of k
litellm/secret_managers/secret_manager_handler.py:76
↓ 7 callers
Method
get_source
Return the provenance of an in-memory guardrail.
litellm/proxy/guardrails/guardrail_registry.py:992
↓ 7 callers
Method
get_standard_logging_payload_trace_id
Returns the `litellm_trace_id` for this request This helps link sessions when multiple requests are made in a single session
litellm/litellm_core_utils/litellm_logging.py:7530
↓ 7 callers
Function
get_team_daily_activity
Get daily activity for specific teams or all teams. Args: team_ids (Optional[str]): Comma-separated list of team IDs to filter by. I
litellm/proxy/management_endpoints/team_endpoints.py:7425
↓ 7 callers
Method
get_tenant_logging_metadata
(user_api_key_dict: UserAPIKeyAuth)
litellm/proxy/litellm_pre_call_utils.py:1654
↓ 7 callers
Method
get_unsupported_headers
Get headers with null values for a provider.
tests/unit/test_anthropic_beta_headers_filtering.py:74
↓ 7 callers
Method
get_usage_from_response_obj
(response_obj: dict | None, combined_usage_object: Usage | None = None)
litellm/litellm_core_utils/litellm_logging.py:7158
↓ 7 callers
Method
get_user_email
(self, token: dict, default_value: str | None)
litellm/proxy/auth/handle_jwt.py:677
↓ 7 callers
Function
get_user_env_vars
Return the calling user's env var dict for ``server_id`` (empty if none).
litellm/proxy/mcp_server/db.py:2456
↓ 7 callers
Method
get_user_id
(self, token, default_value)
tests/unit/proxy/mcp_server/test_id_jag_grant.py:514
↓ 7 callers
Function
get_user_info_from_db
( result: CustomOpenID | OpenID | dict, prisma_client: PrismaClient, user_api_key_cache: UserApiKe
litellm/proxy/management_endpoints/ui_sso.py:2006
↓ 7 callers
Method
get_vertex_ai_location
(litellm_params: dict)
litellm/llms/vertex_ai/vertex_llm_base.py:1211
↓ 7 callers
Method
get_vertex_credentials
Get the vertex credentials for the given project-id, location
litellm/proxy/pass_through_endpoints/passthrough_endpoint_router.py:388
↓ 7 callers
Function
get_vertex_model_id_from_url
Get the vertex model id from the url `https://${LOCATION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/publishe
litellm/llms/vertex_ai/common_utils.py:1254
↓ 7 callers
Function
gf
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 7 callers
Function
go_api_base
(api_base: str | None, model: str = "")
litellm/llms/opencode/common_utils.py:39
↓ 7 callers
Function
group
( *ids: str, **params: object )
tests/unit/test_router/core/test_retries_health_characterization_failure_exits.py:49
↓ 7 callers
Function
group
( *ids: str, **params: object )
tests/unit/test_router/core/test_streaming_characterization_outcomes.py:44
↓ 7 callers
Function
h
litellm/proxy/_experimental/out/_next/static/chunks/11et800l-khs-.js:49
↓ 7 callers
Function
h2
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 7 callers
Function
hJ
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 7 callers
Method
handle_accumulated_json_chunk
(self, chunk: str, is_final: bool = False)
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:4501
↓ 7 callers
Function
handle_any_messages_to_chat_completion_str_messages_conversion
Handles any messages to chat completion str messages conversion Relevant Issue: https://github.com/BerriAI/litellm/issues/9494
litellm/litellm_core_utils/prompt_templates/common_utils.py:229
↓ 7 callers
Method
handle_request
(self, request: httpx.Request)
litellm/llms/custom_httpx/mock_transport.py:90
↓ 7 callers
Function
handle_sampling_create_message
Handle an MCP sampling/createMessage request by routing through LiteLLM. This is the main entry point called by the MCP client session when a
litellm/proxy/mcp_server/sampling_handler.py:1138
↓ 7 callers
Function
has_compresr_retrieve_tool
(tools: object)
litellm/proxy/guardrails/guardrail_hooks/compresr/compresr.py:317
↓ 7 callers
Function
has_user_setup_sso
Check if the user has set up single sign-on (SSO). Covers OAuth providers (Microsoft, Google, generic) and SAML IdP metadata. Used by UI
litellm/proxy/auth/auth_utils.py:1832
↓ 7 callers
Method
hash_token
(self, token)
tests/unit/proxy/spend_tracking/test_spend_management_endpoints.py:4183
↓ 7 callers
Method
header_string
Render headers as the ``k=v,k2=v2`` form an ``ExporterSpec`` expects. Values are percent-encoded because ``providers.parse_headers`` decodes
litellm/integrations/otel/model/destination.py:69
↓ 7 callers
Function
headers
(stream: object)
tests/unit/test_router/core/test_streaming_characterization_anthropic.py:75
↓ 7 callers
Function
headers_of
(response: object)
tests/unit/test_router/core/retries_health_helpers.py:109
↓ 7 callers
Method
health
(self)
litellm/router_core.py:34
↓ 7 callers
Function
heuristicScoringRole
(value: ComplexityRouterConfigValue)
ui/litellm-dashboard/src/components/add_model/ComplexityRouterConfig.tsx:167
↓ 7 callers
Function
heuristic_v1_router_fingerprint
The identity/fingerprint pair for a heuristic-v1 complexity router, else None.
litellm/router_strategy/auto_router/auto_router_tuning_baseline.py:95
↓ 7 callers
Method
history
(self, ctx: SessionContext)
tests/unit/harness/core_fakes.py:198
↓ 7 callers
Method
history
(self)
tests/e2e/migrations/database.py:75
↓ 7 callers
Function
host_in_loop_probing_vault
(monkeypatch: pytest.MonkeyPatch, *secret_names: str)
tests/unit/llms/bedrock/event_loop_probe.py:78
↓ 7 callers
Function
hot_routes_first
(routes: Sequence[BaseRoute])
litellm/proxy/route_priority.py:32
↓ 7 callers
Function
hydrateComplexityRouterConfig
( parsedConfig: StoredComplexityRouterConfig, complexityRouterDefaultModel: string | null | undefined, )
ui/litellm-dashboard/src/components/edit_auto_router/hydrate_complexity_router_config.ts:53
↓ 7 callers
Function
i
litellm/proxy/_experimental/out/_next/static/chunks/269vry4mb17-_.js:3
↓ 7 callers
Function
i$
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 7 callers
Function
ie
(t,e,r,n)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
← previous
next →
10,901–11,000 of 202,479, ranked by callers