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
↓ 10 callers
Function
cli_context_obj
(view: _CliContextObjView)
litellm/proxy/client/cli/commands/auth.py:111
↓ 10 callers
Method
clone
(&self)
litellm-rust/crates/coroutine/src/co.rs:18
↓ 10 callers
Method
close
(self)
tests/unit/caching/test_evicted_client_closer.py:58
↓ 10 callers
Function
collect_files
Wait until `count` flushed files exist, then return every stored payload.
tests/integration/observability/_azure_storage_support.py:200
↓ 10 callers
Function
collect_other_routers
Drop unreachable routers from earlier tests: retire() and runtime pre-call-check changes look at every live router in the process, not only the on
tests/unit/test_router/core/construction_precall_helpers.py:73
↓ 10 callers
Function
config
( *, classifier: Mapping[str, object] | None = None, picker: str = "efficient_first", threshold: float | N
tests/unit/router_strategy/switchyard_router/test_switchyard_router.py:32
↓ 10 callers
Function
config
(verify: Verify)
litellm-rust/crates/http/tests/websocket.rs:102
↓ 10 callers
Method
configure
(self, config: MuseSessionConfig)
litellm/llms/meta/realtime/transformation.py:318
↓ 10 callers
Function
connect
( address: SocketAddr, connection: &'static str, )
litellm-rust/crates/gateway-forward/tests/websocket.rs:38
↓ 10 callers
Function
content_policy
(model: str = "gpt-4o")
tests/unit/test_router/core/scripted_host.py:133
↓ 10 callers
Function
context
(session: ServerSession, revision: str = "2026-07-28")
tests/unit/proxy/mcp_server/test_subscriptions.py:38
↓ 10 callers
Function
convert
( args: tuple[object, ...], kwargs: dict[str, object], # mutable-ok: the call's own k
litellm/router_deprecated.py:873
↓ 10 callers
Function
convert_anyof_null_to_nullable
(schema, depth=0)
litellm/llms/vertex_ai/common_utils.py:1043
↓ 10 callers
Function
convert_to_anthropic_tool_result
OpenAI message with a tool result looks like: { "tool_call_id": "tool_1", "role": "tool", "name": "get_current_weathe
litellm/litellm_core_utils/prompt_templates/factory.py:1822
↓ 10 callers
Method
convert_to_image_response
( response_object: dict, model_response_object: ImageResponse | None = None, hidden_pa
litellm/litellm_core_utils/llm_response_utils/convert_dict_to_response.py:600
↓ 10 callers
Function
convert_to_streaming_response_async
Asynchronously converts a response object to a streaming response. Args: response_object (Optional[dict]): The response object to be
litellm/litellm_core_utils/llm_response_utils/convert_dict_to_response.py:298
↓ 10 callers
Function
cooldowns
()
litellm-rust/crates/redis-store/tests/support/mod.rs:151
↓ 10 callers
Function
cost_per_token
Calculates the cost per token for a given model, prompt tokens, and completion tokens. Input: - model: str, the model name without p
litellm/llms/azure/cost_calculation.py:10
↓ 10 callers
Function
count_input_tokens_for_model
(request_body: dict, model: str)
litellm/proxy/spend_tracking/input_tokens.py:224
↓ 10 callers
Function
create
Sync: Create a managed agent on the provider side. Args: id: Identifier for the agent. Exactly one of ``id`` or its alias ``name`` i
litellm/interactions/agents/main.py:265
↓ 10 callers
Method
create_azure_base_url
( self, azure_client_params: dict, model: str | None, base_model: str | None =
litellm/llms/azure/azure.py:939
↓ 10 callers
Method
create_error_response
Create an Anthropic-formatted error response dict. Anthropic error format: { "type": "error", "error
litellm/anthropic_interface/exceptions/exception_mapping_utils.py:45
↓ 10 callers
Method
create_llm_obs_payload
(self, kwargs: dict, start_time: datetime, end_time: datetime)
litellm/integrations/datadog/datadog_llm_obs.py:629
↓ 10 callers
Function
create_missing_views
-------------------------------------------------- NOTE: Copy of `litellm/db_scripts/create_views.py`. ----------------------------------
litellm/proxy/db/create_views.py:51
↓ 10 callers
Function
create_mock_response
(status_code: int, text: str = "")
tests/unit/secret_managers/test_cyberark_secret_manager.py:215
↓ 10 callers
Function
create_model_group
Create a new access group containing multiple model names. An access group is a named collection of model groups that can be referenced
litellm/proxy/management_endpoints/model_access_group_management_endpoints.py:800
↓ 10 callers
Function
create_object_audit_log
Create an audit log for an internal user. Parameters: - user_id: str - The id of the user to create the audit log for. - action: AUD
litellm/proxy/management_helpers/audit_logs.py:217
↓ 10 callers
Function
create_toolset
(scenario: Scenario, tools: tuple[tuple[str, str], ...], toolset_name: str | None = None)
tests/integration/_support/mcp_grants.py:54
↓ 10 callers
Method
custom
(reply: Result<Option<Secret>, ()>)
litellm-rust/crates/secrets/tests/resolution.rs:170
↓ 10 callers
Function
decode_character_id_with_provider
Decode provider and model_id from encoded character_id.
litellm/types/videos/utils.py:192
↓ 10 callers
Function
decrypt_guardrail_litellm_params
Decrypt values written by encrypt_guardrail_litellm_params; plaintext values pass through unchanged.
litellm/proxy/guardrails/guardrail_registry.py:177
↓ 10 callers
Function
deferred_tools
()
tests/integration/providers/test_chat_completions_tool_search_wire.py:121
↓ 10 callers
Method
delete_cache
Delete a key from the cache
litellm/caching/dual_cache.py:678
↓ 10 callers
Method
delete_prompts_by_base_id
Delete matching prompts from memory, along with their registered callbacks, scoped to one environment when given. Returns th
litellm/proxy/prompts/prompt_registry.py:318
↓ 10 callers
Method
delete_team
(self, team_id: str)
tests/e2e/management/management_client.py:363
↓ 10 callers
Method
deliver
Upload one UTC day: request a signed URL for the window's start day, then PUT the CSV to it.
litellm/integrations/focus/destinations/ternary_destination.py:113
↓ 10 callers
Method
deliver
(self, message: str)
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:5859
↓ 10 callers
Method
deployment_callback_on_success
Count a success and the call's tokens and request against a tracked deployment; returns the counter's key, as the sync callback does.
litellm/router_rust/surface/health.py:535
↓ 10 callers
Function
deployment_pricing_model_info
Pricing the router registered under this deployment's model_info.id. Returns None when the deployment declares no pricing of its own, so the
litellm/litellm_core_utils/litellm_logging.py:495
↓ 10 callers
Function
df
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:8
↓ 10 callers
Function
document
(source: Mapping[str, JsonValue], **fields: JsonValue)
tests/integration/_support/pdf_document.py:105
↓ 10 callers
Function
drain_into
Append every item of an async stream to ``seen``, letting an error the stream raises propagate.
tests/unit/test_router/core/streaming_helpers.py:437
↓ 10 callers
Function
dropping_reply
(chunks: tuple[bytes, ...], *, abort_after: int)
tests/integration/_support/anthropic_sse.py:123
↓ 10 callers
Function
dynamic_mcp_route
Handle /{name}/mcp for MCP server aliases, toolsets, MCP access group tags, and comma-separated lists. Resolution order: 1. Registered MCP se
litellm/proxy/proxy_server.py:22870
↓ 10 callers
Function
e$
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 10 callers
Function
eB
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:1
↓ 10 callers
Function
eJ
({initialValues:e,roleOptions:t,updateSettings:a,onCancel:l,onSaved:r})
litellm/proxy/_experimental/out/_next/static/chunks/37cr8te-omsl0.js:1
↓ 10 callers
Function
eS
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 10 callers
Function
eY
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 10 callers
Function
ee
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 10 callers
Function
ei
litellm/proxy/_experimental/out/_next/static/chunks/2s7apn3nfa3q3.js:1
↓ 10 callers
Method
emit
(&self, event: CallEvent)
litellm-rust/crates/host/src/observation.rs:20
↓ 10 callers
Function
emitTagAndPreviousTextNode
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 10 callers
Function
encode
Encodes the given text using the specified model. Args: model (str): The name of the model to use for tokenization. custom_t
litellm/utils.py:3080
↓ 10 callers
Function
encoded
(raw: bytes)
tests/integration/_support/pdf_document.py:89
↓ 10 callers
Function
encrypt_bearer_token
AES-256-GCM as unpadded base64url behind ``prefix``, which is also the AAD so a token can't change kind.
litellm/proxy/common_utils/encrypt_decrypt_utils.py:182
↓ 10 callers
Function
enrich_cohere_param_description
Embed schema constraints into a Cohere parameter description. ``CohereParameterDefinition`` only has ``type``, ``description``, and ``isRequi
litellm/llms/oci/common_utils.py:657
↓ 10 callers
Method
ensure_partitions
Ensure the current and upcoming partitions exist, returning the names now present. CREATE TABLE IF NOT EXISTS is a no-op for partitio
litellm/proxy/db/db_transaction_queue/spend_logs_partition_manager.py:216
↓ 10 callers
Function
ensure_private_dir
Create directory (and parents) owner-only, tightening it if it already exists group/world readable
litellm/litellm_core_utils/private_json.py:12
↓ 10 callers
Method
entries
(self, response_id: str, name: str)
tests/integration/observability/test_content_filter_logging_only.py:216
↓ 10 callers
Method
environment
(self, **poll: str)
tests/integration/spend/test_background_interaction_settlement.py:131
↓ 10 callers
Function
error_event
(error: Mapping[str, JsonValue] | None)
tests/integration/_support/responses_stream.py:39
↓ 10 callers
Function
eval
`RedisBatch`'s `_Increment`: `INCRBYFLOAT`, then `EXPIRE` when the increment carries a TTL. On its own it keeps a TTL the key already has, like `async
litellm-rust/crates/redis-store/src/rate_limits/scripts.rs:163
↓ 10 callers
Function
evaluate
Every reported metric with its observed value and the case's limit if it has one, plus one line per limit that was exceeded or that the run could
tests/e2e/perf/setup/observe.py:555
↓ 10 callers
Method
execute
()
litellm/caching/redis_cache.py:1015
↓ 10 callers
Function
expand_model_latest_alias
(model: str)
litellm/litellm_core_utils/model_latest_aliases.py:60
↓ 10 callers
Method
extract
(e,t=this._def)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 10 callers
Method
extract
(&self, parts: &Parts)
litellm-rust/crates/gateway-auth/src/http.rs:18
↓ 10 callers
Function
ez
()
litellm/proxy/_experimental/out/_next/static/chunks/37cr8te-omsl0.js:1
↓ 10 callers
Function
f
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 10 callers
Function
f
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:53
↓ 10 callers
Function
f
()
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:1
↓ 10 callers
Method
failed
(self, step: Mapping[str, object])
litellm/router_rust/core.py:5553
↓ 10 callers
Method
failure_handler
( self, exception: Exception, traceback_exception: str, start_time: datetime.d
tests/unit/litellm_core_utils/audio_utils/test_transcription_streaming.py:81
↓ 10 callers
Method
fallback
(&self)
litellm-rust/crates/cost/src/price/meter.rs:119
↓ 10 callers
Method
fetch
(self, user_id: str, server_id: str)
litellm/proxy/mcp_server/outbound_credentials/oauth_token_store.py:277
↓ 10 callers
Method
fetch
(self, user_id: str, server_id: str)
litellm/proxy/mcp_server/outbound_credentials/per_user_oauth_store.py:204
↓ 10 callers
Function
fetch_well_known_card
Fetch an agent card from ``base_url`` using the strategy chosen by ``discovery_mode``. Returns the parsed JSON from the first path that r
litellm/proxy/a2a/discovery.py:88
↓ 10 callers
Method
fields_set
(self)
litellm/types/llms/base.py:21
↓ 10 callers
Function
file_content
(file_id: str)
tests/integration/management/_batch_file_caps.py:64
↓ 10 callers
Function
filter_tools_by_allowed_tools
Filter tools by allowed/disallowed tools configuration. If allowed_tools is set, only tools in that list are returned. If disallowed_too
litellm/proxy/mcp_server/operations.py:792
↓ 10 callers
Function
final
(text: str)
tests/unit/harness/handlers/test_deepagents_handler.py:53
↓ 10 callers
Method
find_many
(self)
litellm/proxy/management_endpoints/key_management_endpoints.py:304
↓ 10 callers
Method
find_spec
( self, fullname: str, path: Sequence[str] | None = None, target: ModuleType |
tests/unit/integrations/conftest.py:86
↓ 10 callers
Method
find_unique
(self, where: Mapping[str, object])
litellm/proxy/mcp_server/toolset_db.py:57
↓ 10 callers
Function
fips_mode_active
Whether general_settings.fips_mode was on when enforce_fips_mode last accepted it.
litellm/proxy/common_utils/fips.py:98
↓ 10 callers
Method
flush_queue
(self)
litellm/integrations/generic_api/generic_api_callback.py:354
↓ 10 callers
Function
flush_request_errors
Scheduler entrypoint. Only cancellation propagates: a metering failure must not kill the job.
litellm/proxy/db/request_error_tracking.py:317
↓ 10 callers
Method
from_cases
(cls, cases: Iterable[HarnessCase])
tests/rust-python-harness/shared/reporting/models.py:190
↓ 10 callers
Method
from_db
Read the authoritative spend for a counter from the DB. Returns the spend value (including 0.0) when the DB is reachable and
litellm/proxy/db/spend_counter_reseed.py:121
↓ 10 callers
Function
g
(t)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 10 callers
Function
get
( pool: &HttpClientPool, config: &HttpClientConfig, variant: ClientVariant, ur
litellm-rust/crates/http/src/pool.rs:198
↓ 10 callers
Function
getLoginUrl
(baseUrl: string = "")
ui/litellm-dashboard/src/utils/returnUrlUtils.ts:16
↓ 10 callers
Function
getSpendString
(value: number | null | undefined, decimals: number = 6)
ui/litellm-dashboard/src/utils/dataUtils.ts:51
↓ 10 callers
Method
get_agent_by_name
Get an agent by its name from the database
litellm/proxy/agent_endpoints/agent_registry.py:945
↓ 10 callers
Method
get_allowed_mcp_servers
(self, user_api_key_auth: UserAPIKeyAuth)
litellm/proxy/mcp_server/server_resolution.py:30
↓ 10 callers
Method
get_attached_policies_with_reasons
Get list of policy names and match reasons for the given context. Returns a list of dicts with 'policy_name' and 'matched_via' keys.
litellm/proxy/policy_engine/attachment_registry.py:145
↓ 10 callers
Method
get_available_deployment
(self, model: str)
tests/unit/test_router/core/test_selection.py:652
↓ 10 callers
Method
get_cache
(self, key: str)
litellm/router_strategy/least_busy.py:216
↓ 10 callers
Method
get_complete_url
( self, api_base: str | None, api_key: str | None, model: str, endpoin
litellm/llms/bedrock/passthrough/transformation.py:431
← previous
next →
7,001–7,100 of 202,479, ranked by callers