MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 6 callersFunctionmigration_environment
(environment: Mapping[str, str])
litellm-proxy-extras/litellm_proxy_extras/migration_lock.py:53
↓ 6 callersFunctionmigration_lock
( database_url: str, lock: AdvisoryLock = COORDINATOR_LOCK, )
litellm-proxy-extras/litellm_proxy_extras/migration_lock.py:122
↓ 6 callersFunctionmigration_names
(database: Database)
tests/e2e/migrations/upgrade.py:109
↓ 6 callersFunctionmo
({layout:e,itemConstraints:t})
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 6 callersFunctionmockAuthorizedUser
(userRole: string, userId: string, premiumUser: boolean)
ui/litellm-dashboard/src/components/add_model/AddModelForm.integration.test.tsx:223
↓ 6 callersFunctionmock_stream
()
tests/unit/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py:2312
↓ 6 callersFunctionmock_stream
()
tests/unit/proxy/guardrails/guardrail_hooks/openai/test_openai_moderation_streaming.py:35
↓ 6 callersFunctionmodelCreateCall
(accessToken: string, formValues: Model)
ui/litellm-dashboard/src/components/networking.tsx:744
↓ 6 callersFunctionmodelInfoCall
( accessToken: string, userID: string, userRole: string, page: number = 1, size: number = 50, sear
ui/litellm-dashboard/src/components/networking.tsx:1624
↓ 6 callersFunctionmodelMaxBudgetUpdate
( edited: ModelMaxBudget, stored: StoredModelMaxBudget | null | undefined, )
ui/litellm-dashboard/src/components/key_team_helpers/modelMaxBudgetPayload.ts:41
↓ 6 callersFunctionmodel_access_group_registry_cache_key
Cache key for the set of model access group names that have a budget row.
litellm/proxy/common_utils/user_api_key_cache.py:541
↓ 6 callersMethodmodel_dump
(self, *, mode: str)
litellm/a2a_protocol/utils.py:22
↓ 6 callersMethodmodel_dump
(self, *, exclude_none: bool)
litellm/proxy/hooks/mcp_semantic_filter/hook.py:55
↓ 6 callersMethodmodel_dump
(self)
litellm/router_strategy/adaptive_router/hooks.py:156
↓ 6 callersFunctionmodel_id
(response: object)
tests/unit/test_router/core/test_streaming_characterization_chat.py:58
↓ 6 callersFunctionmodel_id_of
The deployment the proxy served this response from, as it reports it.
tests/e2e/router/reliability_support.py:373
↓ 6 callersFunctionmodel_info_v1
Provides more info about each model in /models, including config.yaml descriptions (except api key and api base) Parameters: litellm
litellm/proxy/proxy_server.py:18504
↓ 6 callersFunctionmodel_usage
(candidate: Gateway, key: str, model: str)
tests/integration/management/test_budget_reset_windows.py:202
↓ 6 callersMethodmoderation
(**_: object)
tests/unit/proxy/test_common_request_processing.py:13606
↓ 6 callersMethodmoderations
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:14
↓ 6 callersFunctionn1
(e,t,n,s)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 6 callersMethodnew
Add a new model to the proxy. Args: model_name (str): Name of the model to add model_params (Dict[str, Any])
litellm/proxy/client/models.py:75
↓ 6 callersFunctionnewKeyBlockTestResourceData
(t *testing.T, key string)
terraform/provider/litellm/resource_key_block_test.go:17
↓ 6 callersFunctionnewKeyUpdateResourceData
newKeyUpdateResourceData builds a *schema.ResourceData reflecting a real state -> config diff for team_id (unlike schema.TestResourceDataRaw, which ha
terraform/provider/litellm/resource_key_test.go:1282
↓ 6 callersFunctionnewPromptTestData
(t *testing.T, raw map[string]interface{})
terraform/provider/litellm/resource_prompt_test.go:12
↓ 6 callersMethodnew_workspace
(self, files: Mapping[str, str])
tests/e2e/codex/harness.py:62
↓ 6 callersFunctionnh
(s,o,i)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 6 callersMethodnodesBetween
(e,t,n,s=0,r)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 6 callersMethodnormalize_config
Normalize guardrails config to dict format. Accepts: - List of guardrail names: ["g1", "g2"] -> {"g1": None, "g2": None}
litellm/proxy/pass_through_endpoints/passthrough_guardrails.py:44
↓ 6 callersFunctionnormalize_datadog_tag_value
(value: object)
litellm/integrations/datadog/datadog_handler.py:40
↓ 6 callersMethodnormalize_logging_result
Some endpoints return a different type of result than what is expected by the logging system. This function is used to normalize the
litellm/litellm_core_utils/litellm_logging.py:3010
↓ 6 callersFunctionnormalized_audio_duration_seconds
(value: object)
litellm/litellm_core_utils/audio_utils/utils.py:24
↓ 6 callersFunctionnormalized_github_host
(raw: object)
litellm/llms/github_copilot/github_host.py:31
↓ 6 callersFunctionnormalized_tokens
Azure's normalized token count for one request: uncached input in full, cached input at the model's cached ratio, output weighted by the output-to
litellm/llms/azure/ptu_capacity.py:127
↓ 6 callersFunctionnumber
(value: JsonValue)
tests/integration/providers/_gemini_long_decode_support.py:566
↓ 6 callersFunctiono
(e,t,r)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:1
↓ 6 callersFunctionobject_items
(value: object)
litellm/litellm_core_utils/llm_cost_calc/guardrail_cost.py:121
↓ 6 callersFunctionobservation_attributes
The observation's own fields, serialized the way the SDK's ``create_generation_attributes`` does. ``prompt`` links the generation to a managed pr
litellm/integrations/langfuse/langfuse_sdk.py:248
↓ 6 callersFunctionobserve
(cache, request_body=None, native_usage=None, now=1010.0, **overrides)
tests/unit/proxy/hooks/test_prompt_cache_observer.py:72
↓ 6 callersMethodocr
(self, key: str, body: OcrBody)
tests/e2e/proxy_client.py:1062
↓ 6 callersFunctionopenPlayground
(page: PlaywrightPage)
tests/e2e/ui/helpers/playground.ts:18
↓ 6 callersFunctionopen_bridge_refresh_envelope
Open a refresh envelope a bridge ``oauth_delegate`` client presented on a refresh_token grant. The token-endpoint mirror of :func:`resolve_bridge
litellm/proxy/mcp_server/outbound_credentials/bridge_credentials.py:145
↓ 6 callersFunctionopen_chat
(core: RouterCore, model: str = "g")
tests/unit/test_router/core/test_streaming_characterization_outcomes.py:50
↓ 6 callersFunctionopenai_edge
(cache: CacheEdge, provider: Provider, path: str)
tests/code_coverage_tests/test_provider_cache.py:784
↓ 6 callersFunctionopenai_proxy_route
Pass-through endpoint for OpenAI API calls. Available on both routes: - /openai/{endpoint:path} - Standard OpenAI passthrough route
litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:3374
↓ 6 callersMethodopenai_receives
( self, model: str, messages: Sequence[JsonValue], *, stream: bool = False, tools: Sequence[JsonValue]
tests/integration/providers/test_openai_chat_prompt_cache_breakpoint_wire.py:46
↓ 6 callersFunctionopencode_model_sync_env
Env addition that hands OpenCode the proxy's model list, or why it was skipped. Fetches /v1/models with the key, and /model_group/info for each m
litellm/proxy/client/cli/commands/agents.py:714
↓ 6 callersFunctionordered
(**arguments: object)
tests/unit/test_router/core/test_parity_cooldown_service_model.py:147
↓ 6 callersFunctionorg_counter
(org_id: str)
litellm/redis/stores/spend_counters/types.py:44
↓ 6 callersMethodorigin
(self)
litellm/router_rust/invoke/streaming.py:131
↓ 6 callersFunctionotel_unhandled_exception_handler
(request: Request, exc: Exception)
litellm/proxy/proxy_server.py:2570
↓ 6 callersFunctionotlp_http_exception_handler
(connection: Request | WebSocket, exc: StarletteHTTPException)
litellm/proxy/proxy_server.py:2380
↓ 6 callersFunctionparams
(value: Value)
litellm-rust/crates/llms/src/openai_like/chat/transformation.rs:306
↓ 6 callersFunctionparent_session_kwargs
(request_kwargs: Mapping[str, object] | None)
litellm/litellm_core_utils/internal_call_metadata.py:229
↓ 6 callersMethodparse
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 6 callersFunctionparseJson
(raw: string)
ui/litellm-dashboard/src/app/(dashboard)/playground/components/systemOneUI/lib/validatePayload.ts:50
↓ 6 callersFunctionparse_cost_discount_key
(key: str)
litellm/litellm_core_utils/cost_discount.py:20
↓ 6 callersFunctionparse_event
(obj: dict, state: CodexStreamState)
tests/unit/llms/codex/harness/test_transformation.py:51
↓ 6 callersMethodparse_frontmatter
Parse YAML frontmatter from prompt content.
litellm/integrations/dotprompt/prompt_manager.py:186
↓ 6 callersMethodparse_policy
Parse a policy from raw configuration data. Args: policy_name: Name of the policy policy_data: Raw policy co
litellm/proxy/policy_engine/policy_registry.py:221
↓ 6 callersFunctionparse_sse_frames
(body: str)
tests/integration/translation/runner.py:121
↓ 6 callersMethodpartial_response_on_disconnect
(self)
litellm/router_rust/invoke/streaming.py:1604
↓ 6 callersFunctionpdf_data_url
(pages: Sequence[Page])
tests/integration/_support/pdf_document.py:97
↓ 6 callersFunctionpeek_reasoning_summary_aliases
Read AI-SDK-style reasoning summary from optional_params or nested extra_body. Uses key membership (not ``or`` chains) so falsy values like ``""`
litellm/litellm_core_utils/model_param_helper.py:28
↓ 6 callersMethodpeer_calls
(self)
tests/integration/mcp/test_mcp_llm_endpoints.py:1756
↓ 6 callersFunctionpending
A store op declared on the batch the caller's `NativeSend` picked, answered as `reply` shapes it.
litellm-rust/crates/python-bridge/src/redis/store/mod.rs:155
↓ 6 callersFunctionpersonal_key_inherits_team_grants
MCP server, MCP tool and agent inheritance is for a virtual key only. A keyless auth with no team (one grant source of an admitted subject, a JWT
litellm/proxy/auth/auth_checks.py:5977
↓ 6 callersFunctionphase_event
Mark a point in the request on its span (no-op without V2).
litellm/integrations/otel/runtime.py:62
↓ 6 callersFunctionpicked
The id ``select`` picks, or the error's class and message.
tests/unit/test_router/core/test_gaps_router_core_crate.py:43
↓ 6 callersFunctionpicks_reserve
(reserve: bool)
litellm/router_strategy/least_busy.py:35
↓ 6 callersFunctionplace_tool_result_images
Move images out of ``toolResult.content`` when this model rejects them there.
litellm/llms/bedrock/chat/tool_result_images.py:11
↓ 6 callersFunctionplaintext_database_url
(database_url: str)
tests/integration/_support/database_relay.py:335
↓ 6 callersMethodpoll
(mut self: Pin<&mut Self>, context: &mut Context<'_>)
litellm-rust/crates/coroutine/src/reply.rs:45
↓ 6 callersMethodpoll_events_for_marker
``poll_events_for_query`` over the every-attribute marker scan.
tests/e2e/logging/datadog_reader.py:163
↓ 6 callersFunctionpopulate_request_with_path_params
Copy FastAPI path params and query params into the request payload so downstream checks (e.g. vector store RBAC, organization RBAC) see them
litellm/proxy/common_utils/http_parsing_utils.py:804
↓ 6 callersFunctionpost_response_phase
Work the caller no longer waits for (success callbacks, response-cache writes), including tasks it spawns.
litellm/_internal_context.py:77
↓ 6 callersMethodprepare_input
Prepare input text for guardrail execution based on field targeting settings. If request_fields is specified, extracts only those fi
litellm/proxy/pass_through_endpoints/passthrough_guardrails.py:117
↓ 6 callersFunctionprepared
(root: Path)
tests/e2e_harness/test_fixture_bundle.py:50
↓ 6 callersMethodprepend_system_prompt
( messages: list[AllMessageValues], # mutable-ok: callers pass the request messages list through
litellm/router_utils/prompt_caching_cache.py:316
↓ 6 callersFunctionprice_cache_tokens
( model: str, deployment_id: str, tokens: CacheTokenBuckets, completion_tokens: int = 0 )
litellm/llms/anthropic/prompt_cache_pricing.py:41
↓ 6 callersFunctionpricing_entry_for_cost_calc
( model: str | None, completion_response: object | None, custom_llm_provider: str | None, cust
litellm/cost_calculator.py:2762
↓ 6 callersFunctionprobe_tool_search
POST to `/v1/messages` with a `tool_search_tool_regex_20251119` tool definition and return the typed result. LiteLLM's `is_tool_search_used`
tests/e2e/claude_code/http_probe.py:134
↓ 6 callersMethodprocess_input_messages
Process OCR input by applying guardrails to the document reference. The OCR input contains a document dict with a URL. We extract
litellm/llms/mistral/ocr/guardrail_translation/handler.py:34
↓ 6 callersMethodprocess_mcp_tools_without_openai_transform
Process MCP tools through filtering and deduplication pipeline without OpenAI transformation. This is useful for cases where we need
litellm/responses/mcp/litellm_proxy_mcp_handler.py:488
↓ 6 callersFunctionproject_counter
(project_id: str)
litellm/redis/stores/spend_counters/types.py:52
↓ 6 callersFunctionprompt_environment_or_default
(environment: str | None)
litellm/proxy/prompts/prompt_registry.py:69
↓ 6 callersFunctionprose
(rng: random.Random, chars: int)
scripts/seed_request_logs.py:60
↓ 6 callersMethodprovider
(self)
litellm-rust/crates/inference-ocr/src/provider_config.rs:102
↓ 6 callersFunctionprovider_http
(resources: &CoreResources, config: &HttpClientConfig)
litellm-rust/crates/inference-testing/src/lib.rs:27
↓ 6 callersFunctionprovider_message
(marker: str)
tests/integration/observability/test_stream_error_alert_api_base.py:171
↓ 6 callersFunctionprovider_request_id_headers
The provider request id headers in `headers` whose values are ASCII strings, or None when there are none.
litellm/litellm_core_utils/llm_response_utils/get_headers.py:22
↓ 6 callersMethodproxy_config
(self)
tests/e2e/secret_manager/secret_store.py:28
↓ 6 callersFunctionpt
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 6 callersFunctionptu_capacity_warning
Why this reserved deployment's tokens cannot be converted to PTUs, else None. Only a deployment that declares shares (whose ceilings need a sizin
litellm/litellm_core_utils/ptu_shares.py:252
↓ 6 callersFunctionpython
()
litellm/proxy/spend_tracking/input_tokens.py:96
↓ 6 callersFunctionpython_settings
(py: Python<'py>, overrides: &str)
litellm-rust/crates/python-bridge/src/http.rs:219
↓ 6 callersFunctionqualified_member_name
(namespace: str, name: str)
litellm/litellm_core_utils/tool_fields.py:70
↓ 6 callersFunctionqualify_provider_stripped_model
Put the provider prefix back on a provider-stripped model.
litellm/litellm_core_utils/core_helpers.py:40
↓ 6 callersMethodquery_help
(self, scope: QueryScope, secret: str)
litellm/tracing/remote.py:188
↓ 6 callersMethodquery_sql
(self, sql: str, scope: QueryScope, secret: str)
litellm/tracing/remote.py:185
← previousnext →13,301–13,400 of 202,479, ranked by callers