MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 12 callersMethodget_model_listing_info
(self, model_name: str)
litellm/router_deprecated.py:609
↓ 12 callersMethodget_optional_params_image_edit
Get optional parameters for the image edit API. Args: model: The model name image_edit_provider_config: The
litellm/images/utils.py:30
↓ 12 callersFunctionget_project_object
Fetch project object from cache or DB. Follows get_team_object() caching pattern with TTL and last_refreshed_at. Returns LiteLLM_Projec
litellm/proxy/auth/auth_checks.py:7496
↓ 12 callersMethodget_prompts_from_server
( self, server: MCPServer, user_api_key_auth: UserAPIKeyAuth | None, mcp_auth_
litellm/proxy/mcp_server/mcp_server_manager.py:4882
↓ 12 callersFunctionget_request_root_path
Return the effective ``root_path`` for the current request. Reads the value ``PerRequestRootPathMiddleware`` stashed for this request; falls
litellm/proxy/middleware/per_request_root_path_middleware.py:36
↓ 12 callersFunctionget_service_tier_cost_key
Get the appropriate cost key based on service tier. Args: base_key: The base cost key (e.g., "input_cost_per_token") service
litellm/litellm_core_utils/llm_cost_calc/utils.py:286
↓ 12 callersFunctionget_ssl_configuration
Unified SSL configuration function that handles ssl_context and ssl_verify logic. SSL Configuration Priority: 1. If ssl_verify is provid
litellm/llms/custom_httpx/http_handler.py:409
↓ 12 callersFunctionget_token_count
(messages, model)
litellm/utils.py:8848
↓ 12 callersMethodget_tools_from_server
( self, server: MCPServer, mcp_auth_header: str | dict[str, str] | None = None,
litellm/proxy/mcp_server/mcp_server_manager.py:4428
↓ 12 callersMethodget_unhealthy_deployment_ids
Sync version: return set of deployment IDs currently marked unhealthy and not stale.
litellm/router_utils/health_state_cache.py:126
↓ 12 callersMethodget_usage_data
Retrieve usage data from LiteLLM daily user spend table.
litellm/integrations/cloudzero/database.py:40
↓ 12 callersFunctionget_vertex_url
( mode: all_gemini_url_modes, model: str, stream: bool | None, vertex_project: str | None,
litellm/llms/vertex_ai/common_utils.py:556
↓ 12 callersMethodgroup
(&self, name: &str)
litellm-rust/crates/router-core/src/registry.rs:919
↓ 12 callersFunctionguardrail_config
(policy_url: str, path: Path)
tests/integration/authorization/_guardrail_opt_out.py:23
↓ 12 callersFunctionguardrail_information_cost
(guardrail_information: object)
litellm/litellm_core_utils/llm_cost_calc/guardrail_cost.py:306
↓ 12 callersMethodhandle
(self, request: httpx.Request)
tests/unit/proxy/common_utils/test_codex_catalog_source.py:33
↓ 12 callersMethodhandle_async_request
( self, request: httpx.Request, )
litellm/llms/custom_httpx/aiohttp_transport.py:445
↓ 12 callersMethodhas_policy
Check if a policy exists. Args: policy_name: Name of the policy to check Returns: True if policy ex
litellm/proxy/policy_engine/policy_registry.py:308
↓ 12 callersFunctionheaders
(response: object)
tests/unit/test_router/core/test_fallbacks.py:44
↓ 12 callersFunctionhistory
(surface: Surface)
tests/unit/router_strategy/complexity_router/test_context_compaction.py:94
↓ 12 callersMethodhuggingface
(&self)
litellm-rust/crates/python-bridge/src/tokenizer.rs:556
↓ 12 callersMethodimage_generation
(self, optional_params: dict[str, object], **kwargs: object)
tests/unit/images/test_main.py:730
↓ 12 callersMethodincrement
(self, key: str, value: float, ttl: int | None = None)
litellm/caching/redis_batch.py:332
↓ 12 callersMethodinitialize_prompt
Initialize a guardrail from a dictionary and add it to the litellm callback manager Returns a Guardrail object if the guardrail is i
litellm/proxy/prompts/prompt_registry.py:185
↓ 12 callersMethodinject_advisory_message
Append an advisory system message to the request in place, so the LLM itself can weigh a possible false-positive guardrail flag rathe
litellm/integrations/custom_guardrail.py:570
↓ 12 callersMethodinstall
(self)
tests/unit/router_utils/test_fallback_event_handlers.py:2006
↓ 12 callersMethodinstall
( &self, agent: &impl Install, version: &Version, )
litellm-rust/crates/testkit/src/install/mod.rs:40
↓ 12 callersFunctioninstall_fake_keyring
(monkeypatch)
tests/unit/litellm_core_utils/test_cli_token_utils.py:1189
↓ 12 callersFunctioninstall_statusline_script
( script_path: Path | None = None, *, package_version: str = litellm_version, write: Callable[
litellm/proxy/client/cli/commands/claude_settings.py:335
↓ 12 callersFunctioninvoke
( route: Literal["chat", "messages", "responses"], server: RecordingServer, options: Mapping[str,
tests/test_litellm_rust/cache/support.py:39
↓ 12 callersMethodis_initialized
(self)
litellm/proxy/db/tool_registry_writer.py:420
↓ 12 callersFunctionis_mcp_admitted_user_subject
True when this auth is a keyless subject admitted by the gateway session / bridge user path, as opposed to a JWT or other keyless auth that merely
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:428
↓ 12 callersFunctionis_offline_mode
True when ``LITELLM_OFFLINE_MODE=true``. A catalog, check or tokenizer LiteLLM fetches on its own, rather than from a destination the operator con
litellm/litellm_core_utils/offline_mode.py:4
↓ 12 callersMethodis_recording
(self)
tests/unit/integrations/otel/test_otel_v2_mount.py:101
↓ 12 callersMethodis_request_https
Whether this request's PUBLIC-facing origin is HTTPS, for deciding whether a cookie set on the response should be marked ``Secure``.
litellm/proxy/auth/ip_address_utils.py:200
↓ 12 callersFunctionis_sso_provider_fully_configured
Whether ANY configured SSO provider has every companion setting it needs to actually authenticate a user, not merely a client id. A lone ``MI
litellm/proxy/auth/auth_utils.py:1894
↓ 12 callersMethodis_sync_litellm_request
True for sync SDK entrypoints (``completion``), false for async (``acompletion``, etc.).
litellm/litellm_core_utils/litellm_logging.py:2518
↓ 12 callersMethodis_team_within_model_budget
(self, team_id, team_model_max_budget, key_model_max_budget, model)
tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py:5282
↓ 12 callersFunctionis_tool_name_prefixed
Check if tool name has a known MCP server prefix. When ``known_server_prefixes`` is provided the function verifies that the name actuall
litellm/proxy/mcp_server/utils.py:502
↓ 12 callersFunctionj
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 12 callersFunctionjson
( url: &str, headers: &[(String, String)], body: &impl Serialize, timeout: Option<Duration>, )
litellm-rust/crates/http/src/outbound.rs:24
↓ 12 callersFunctionjson_reply
(body: dict[str, JsonValue], status: int = 200)
tests/integration/spend/_background_responses.py:83
↓ 12 callersFunctionjwtKeyMappingFixture
()
terraform/provider/litellm/resource_jwt_key_mapping_crud_test.go:67
↓ 12 callersMethodkey
(&self)
litellm-rust/crates/redis-store/src/spend_counters/keys.rs:30
↓ 12 callersMethodkill
(self)
tests/e2e/migrations/containers.py:68
↓ 12 callersMethodkwargs_of
(self, handler_name: str)
tests/unit/videos/test_main.py:76
↓ 12 callersFunctionlabel_values
(samples: Sequence[Sample])
tests/integration/_support/prometheus_series.py:267
↓ 12 callersFunctionlanded
(arrivals: tuple[Arrival, ...])
tests/integration/providers/_idle_upstream_support.py:623
↓ 12 callersFunctionlisted_tools
(gateway: Gateway, key: str, identity: str | None = None)
tests/integration/_support/mcp.py:558
↓ 12 callersFunctionlitellm_fine_tuning_job_from_response
(response: FineTuningJob, is_azure: bool = False)
litellm/llms/openai/fine_tuning/handler.py:52
↓ 12 callersFunctionload_bundle
(root: Path, *, profile: MatchProfile = "legacy")
tests/e2e/fixture_bundle.py:288
↓ 12 callersFunctionload_json_or_empty
(path: Path)
litellm/proxy/client/cli/commands/claude_settings.py:222
↓ 12 callersFunctionm
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 12 callersFunctionmain
main is the entry point for the plugin. It serves the provider using the Terraform plugin SDK.
terraform/provider/main.go:10
↓ 12 callersFunctionmake_config
( issuer_url: str = ISSUER_URL, subject: str = SUBJECT, audience: str | None = None, ttl_secon
tests/unit/llms/base_llm/auth/test_internal_issuer.py:37
↓ 12 callersFunctionmake_ctx
(sandbox=None, **kwargs)
tests/unit/llms/opencode/harness/test_transformation.py:173
↓ 12 callersFunctionmanager
(server: &MockServer, settings: KeyManagementSettings)
litellm-rust/crates/secrets-aws/tests/secret_manager/support.rs:3
↓ 12 callersMethodmap_openai_params
Map OpenAI parameters to Vertex AI TTS parameters Voice handling (similar to Azure AVA): - If voice is an OpenAI voice name
litellm/llms/vertex_ai/text_to_speech/transformation.py:651
↓ 12 callersMethodmap_openai_params
Map parameters for XAI Responses API. Handles XAI-specific transformations: 1. Transforms code_interpreter tools to remove '
litellm/llms/xai/responses/transformation.py:141
↓ 12 callersMethodmap_openai_params
( self, non_default_params: dict, optional_params: dict, model: str, d
litellm/llms/tencent/chat/transformation.py:47
↓ 12 callersMethodmap_openai_params
( self, non_default_params: dict, optional_params: dict, model: str, d
litellm/llms/fireworks_ai/chat/transformation.py:325
↓ 12 callersFunctionmapped
What the configured mappers write on the span, the way the logger stamps it.
tests/unit/integrations/otel/test_otel_v2_destinations.py:5092
↓ 12 callersFunctionmapping
(value: object)
litellm/router_strategy/switchyard_router/translation.py:24
↓ 12 callersFunctionmarked_prompt
()
tests/integration/providers/_sagemaker_chat_container.py:131
↓ 12 callersFunctionmarketplace_entry
(gateway: Gateway, name: str, *, key: str | None = None)
tests/integration/management/test_claude_code_plugin_installation_preference.py:88
↓ 12 callersFunctionmatch_routing_generalization
Return the provider of the first routing rule whose regex matches ``model``. O(number of rules). Only call this once exact lookups have missed.
litellm/litellm_core_utils/fallback_generalizations.py:217
↓ 12 callersFunctionmaybe_schedule_background_interaction_cost_polling
( response: object, create_kwargs: Mapping[str, object], custom_llm_provider: str, store: Back
litellm/interactions/background_cost_polling.py:725
↓ 12 callersMethodmerge
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 12 callersFunctionmessages_body
( model: str, marker: str, *, safeguards: JsonValue | _Omitted = SAFEGUARDS, stream: bool
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_safeguards_beta_wire.py:162
↓ 12 callersMethodmethod
(self)
tests/unit/litellm_core_utils/test_litellm_logging.py:13814
↓ 12 callersFunctionmint_session_refresh_token
Mint the long-lived session REFRESH token for ``principal``. ``exp`` is ``SESSION_REFRESH_TTL_SECONDS`` from ``now``. Minting a distinct ``ki
litellm/proxy/mcp_server/outbound_credentials/session_token.py:356
↓ 12 callersFunctionmock_streaming_response
Simulate an LLM streaming response.
tests/unit/proxy/hooks/test_async_post_call_streaming_iterator_hook.py:51
↓ 12 callersFunctionmodel_budget_start_time_cache_key
Window start for one (entity, budget model) pair. Scoped per budget model because an entity may budget two models over different periods, and
litellm/proxy/hooks/model_max_budget_limiter.py:158
↓ 12 callersFunctionn
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/11et800l-khs-.js:1
↓ 12 callersFunctionn
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:53
↓ 12 callersFunctionn
()
litellm/proxy/_experimental/out/_next/static/chunks/2jxpy6eth1zvy.js:1
↓ 12 callersFunctionnames
(exporter: InMemorySpanExporter)
tests/unit/integrations/otel/test_otel_v2_destinations.py:2519
↓ 12 callersFunctionnames_and_ids
``(model_name, model_info.id)`` of each deployment dict, in order.
tests/unit/test_router/core/registry_helpers.py:20
↓ 12 callersFunctionnon_openai_responses_bridge
( restore_model_registry, respx_mock: respx.MockRouter, monkeypatch: pytest.MonkeyPatch, tmp_path: Path )
tests/unit/test_main.py:2587
↓ 12 callersMethodnormalize
Apply all xAI normalization passes in order.
litellm/llms/xai/realtime/transformation.py:72
↓ 12 callersFunctionnormalize_jsonrpc_response
Convert a JSON-RPC response's ``result`` to ``target``. Errors and non-dict results pass through untouched.
litellm/proxy/a2a/version_convert.py:57
↓ 12 callersMethodobserve
(&self, _event: &RouterEvent)
litellm-rust/crates/router-core/src/build.rs:282
↓ 12 callersFunctionof_marker
(received: tuple[Request, ...], marker: str)
tests/integration/providers/_api_base_trailing_slash_support.py:291
↓ 12 callersMethodof_upstream_unavailable
(detail: str)
litellm/proxy/mcp_server/outbound_credentials/types.py:164
↓ 12 callersMethodoff
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:11
↓ 12 callersMethodon
(&self, provider: BetaProvider)
litellm-rust/crates/llms-types/src/providers/anthropic/beta.rs:290
↓ 12 callersFunctionopen
(gateway: &Gateway, handshake: String)
litellm-rust/crates/gateway-forward/tests/websocket.rs:150
↓ 12 callersFunctionp
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 12 callersFunctionpatch_guardrail
Partially update an existing guardrail 👉 [Guardrail docs](https://docs.litellm.ai/docs/proxy/guardrails/quick_start) This endpoint allo
litellm/proxy/guardrails/guardrail_endpoints.py:1197
↓ 12 callersFunctionplan_pgbouncer
Render the PgBouncer config for ``upstream_url`` and the loopback URL Prisma uses instead. Params describing Prisma's own pool (``connection_limi
litellm/proxy/db/pgbouncer.py:190
↓ 12 callersFunctionproblem_response
(problem: ProblemDetail)
litellm/proxy/list_api/common.py:34
↓ 12 callersFunctionprocess_embed_content_response
Process Gemini embedContent response (single embedding for multimodal input). Args: input: Original input model_response: Em
litellm/llms/vertex_ai/gemini_embeddings/batch_embed_content_transformation.py:570
↓ 12 callersMethodprocess_output_response
Process output response by applying guardrails to text content and tool calls. Args: response: LiteLLM ResponsesAPIRespo
litellm/llms/openai/responses/guardrail_translation/handler.py:1114
↓ 12 callersFunctionprofile_python
(source_root: Path, *, threads: bool = False)
tests/rust-python-harness/shared/tracing/profiler.py:182
↓ 12 callersFunctionproject_cache_key
(project_id: str)
litellm/proxy/common_utils/user_api_key_cache.py:546
↓ 12 callersMethodprompt
Python reads `kwargs["messages"]` unguarded, so a request without messages fails.
litellm-rust/crates/cache-qdrant-semantic/src/cache.rs:86
↓ 12 callersFunctionproperty
({propKey:s,propVal:o,propClass:i})
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 12 callersFunctionpublish_config_change
( redis_cache: "RedisCache | None", object_type: str, model_ids: tuple[str, ...] = () )
litellm/proxy/common_utils/config_sync_pubsub.py:157
↓ 12 callersFunctionraise_for_error_status
(response: httpx.Response, container_provider_config: "BaseContainerConfig")
litellm/llms/custom_httpx/container_handler.py:162
↓ 12 callersMethodread
(self)
litellm/llms/black_forest_labs/image_edit/transformation.py:60
← previousnext →5,601–5,700 of 202,479, ranked by callers