MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 73 callersFunction_as_router
The Router this mixin is part of (it is mixed into ``litellm.Router`` only).
litellm/router_deprecated.py:96
↓ 73 callersMethod_transform_request
( self, model: str, messages: list[AllMessageValues], optional_params: dict,
litellm/llms/bedrock/chat/converse_transformation.py:2416
↓ 73 callersMethodclear_queue
Clear the queue with a maximum time limit.
litellm/litellm_core_utils/logging_worker.py:551
↓ 73 callersFunctiontool_id
(request_nonce: str)
tests/integration/_support/safeguards_rig.py:115
↓ 72 callersFunctionconnect
(redis_cache: RedisCache | None)
litellm/redis/stores/connection.py:48
↓ 72 callersMethodcontains
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 72 callersFunctionget_model_info
Get a dict for the maximum tokens (context window), input_cost_per_token, output_cost_per_token for a given model. Parameters: - model
litellm/utils.py:7769
↓ 72 callersMethodlock
(&self)
litellm-rust/crates/cache-memory/src/cache.rs:92
↓ 72 callersMethodresponse_cost_calculator
(self, result)
tests/unit/proxy/test_common_request_processing.py:10577
↓ 72 callersFunctionservice_account_json
(project: str, token_url: str)
tests/integration/_support/vertex.py:10
↓ 72 callersMethodstart
(self)
tests/integration/_support/process.py:1096
↓ 72 callersFunctionstream_chunk_builder
( chunks: list, messages: Sequence | None = None, start_time: object = None, end_time: object
litellm/litellm_core_utils/streaming_chunk_builder_utils.py:1803
↓ 72 callersMethodthen
(self, builder: ErrorBuilder | None)
tests/unit/test_router/core/retries_health_helpers.py:129
↓ 72 callersFunctionuser_api_key_has_admin_view
Return True if the caller's role grants unscoped read access to all tenant resources (managed files, batches, vector stores, spend rows, etc).
litellm/types/proxy/auth/user_api_key_auth.py:332
↓ 71 callersFunctionb
(e,t,i,a)
litellm/proxy/_experimental/out/_next/static/chunks/3ud9wkq24q2g3.js:1
↓ 71 callersMethodchat
(self, key: str, model: str, text: str)
tests/e2e/logging/logging_client.py:487
↓ 71 callersMethodclear
(self)
tests/integration/_support/device_login.py:217
↓ 71 callersFunctiong
()
litellm/proxy/_experimental/out/_next/static/chunks/3ud9wkq24q2g3.js:1
↓ 71 callersFunctiongemini_convert_messages_with_history
Converts given messages from OpenAI format to Gemini format - Parts must be iterable - Roles must alternate b/w 'user' and 'model' (same
litellm/llms/vertex_ai/gemini/transformation.py:776
↓ 71 callersFunctionpicked_ids
The deployment ids ``select`` picks over ``times`` picks, each with a fresh copy of ``request_kwargs``.
tests/unit/test_router/core/selection_helpers.py:64
↓ 71 callersMethodrecv
(self)
tests/unit/realtime_api/test_main.py:504
↓ 71 callersFunctionupdate_db_model
( db_model: Deployment, updated_patch: updateDeployment, loaded_catalog: LoadedCatalog = GetModelC
litellm/proxy/management_endpoints/model_management_endpoints.py:1490
↓ 71 callersFunctionupstream
Starts an upstream that answers its n-th request with the n-th response and 404s after.
litellm-rust/crates/inference-ocr/tests/support/mod.rs:40
↓ 70 callersMethodasync_set_cache
(self, key, value, local_only: bool = False, **kwargs)
litellm/caching/dual_cache.py:481
↓ 70 callersFunctionchat_reply
(identity: str, model: str, text: str, *, stream: bool)
tests/integration/_support/openai_wire.py:53
↓ 70 callersMethoddrain
(self)
tests/integration/authorization/test_key_guardrail_opt_out_chaos.py:83
↓ 70 callersMethodencode
(self, text: str, /)
litellm/llms/ollama/completion/handler.py:24
↓ 70 callersMethoderror
(self)
litellm/proxy/management_endpoints/auto_router_endpoints.py:182
↓ 70 callersFunctionf
litellm/proxy/_experimental/out/_next/static/chunks/0r8bcbns1_gw5.js:1
↓ 70 callersFunctionfresh_chat
( candidate: Gateway, model: str, key: str, marker: str, extra: Mapping[str, JsonValue] = NO_EXTRA )
tests/integration/authorization/_hidden_alias_budget.py:119
↓ 70 callersMethodincludes
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 70 callersMethoditems
(self)
litellm/responses/streaming_iterator.py:151
↓ 70 callersFunctionparse
(url: &str, body: &[u8])
litellm-rust/crates/testkit/src/install/release.rs:60
↓ 70 callersFunctionsecret_vault_factory
()
tests/unit/litellm_core_utils/conftest.py:7
↓ 69 callersFunction_element
(payload: dict[str, object], key_suffix: str)
tests/unit/integrations/test_s3_v2.py:3082
↓ 69 callersFunction_managed_files_with_fake_prisma
( *rows: LiteLLM_ManagedFileTable, sleep: Callable[[float], Awaitable[None]] = asyncio.sleep, )
tests/unit/enterprise/proxy/hooks/test_managed_files.py:186
↓ 69 callersFunction_user_passthrough_managed
(user_id: str = "user-1", team_id: str = "team-1")
tests/unit/proxy/pass_through_endpoints/test_managed_id_rewriter.py:349
↓ 69 callersMethodas_str
(&self)
litellm-rust/crates/cost/src/call.rs:39
↓ 69 callersMethodclone
(&self)
litellm-rust/crates/host/src/machine/context.rs:34
↓ 69 callersFunctionfrom_str
(json: str)
litellm/rust_bridge/tokenizer.py:103
↓ 69 callersMethodwait_for
(self, marker: str, timeout: float)
tests/integration/sdk/test_redis_cluster_iam_auth.py:28
↓ 68 callersFunction_get_encoding
Get encoding, loading it lazily if needed.
litellm/main.py:9671
↓ 68 callersMethodconnect
(&self)
litellm-rust/crates/gateway-forward/tests/support/mod.rs:72
↓ 68 callersFunctioncost_per_token
Calculates the cost per token for a given model, prompt tokens, and completion tokens. Parameters: model (str): The name of the mode
litellm/cost_calculator.py:490
↓ 68 callersMethodcount
(self, *, where: Mapping[str, object])
tests/unit/repositories/test_chunked_in.py:48
↓ 68 callersMethodheader
(&self, name: &str)
litellm-rust/crates/gateway-forward/tests/support/mod.rs:159
↓ 68 callersFunctionheld
`eventually`, and then `satisfied` must hold on every read for `holding` more seconds; a miss restarts the hold.
tests/integration/_support/client.py:73
↓ 68 callersMethodimage_generation
( self, model: str, prompt: str, api_key: Optional[str], api_base: Opt
tests/unit/llms/test_custom_llm.py:211
↓ 68 callersMethodkeys
(self)
litellm/llms/gemini/count_tokens/handler.py:41
↓ 68 callersFunctionnow
()
litellm-rust/crates/secrets/tests/oidc.rs:200
↓ 68 callersMethodshift
()
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 67 callersFunctionget_team_object
- Check if team id in proxy Team Table - if valid, return LiteLLM_TeamTable object with defined limits - if not, then raise an error
litellm/proxy/auth/auth_checks.py:3704
↓ 67 callersMethodparse
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 67 callersMethodsignature
(self)
tests/integration/authorization/test_rag_team_provider_credentials.py:107
↓ 66 callersFunction_spec
(config)
tests/unit/proxy/mcp_server/outbound_credentials/test_resolver.py:132
↓ 66 callersFunctionaccumulate
(deltas: Sequence[Mapping[str, JsonValue]])
tests/integration/_support/anthropic_thinking.py:229
↓ 66 callersMethodcheck_batch_cost
(self)
tests/unit/proxy/openai_files_endpoint/test_files_common_utils.py:144
↓ 66 callersFunctioncollect_texts
The text content of every chunk of an async chat stream, joined.
tests/unit/test_router/core/streaming_helpers.py:214
↓ 66 callersMethodfindIndex
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 66 callersFunctionnew_team
Allow users to create a new team. Apply user permissions to their team. 👉 [Detailed Doc on setting team budgets](https://docs.litellm.ai/doc
litellm/proxy/management_endpoints/team_endpoints.py:1667
↓ 66 callersMethodnow
(cls, tz=None)
tests/unit/proxy/common_utils/test_reset_budget_job.py:4063
↓ 66 callersMethodpop
()
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 66 callersMethodread
(self)
tests/e2e/perf/setup/run.py:84
↓ 66 callersFunctiontoken_counter
Count the number of tokens in a given text using a specified model. Args: model (str): The name of the model to use for tokenization. De
litellm/litellm_core_utils/token_counter.py:893
↓ 66 callersFunctionw
litellm/proxy/_experimental/out/_next/static/chunks/0r8bcbns1_gw5.js:1
↓ 65 callersFunctionL
litellm/proxy/_experimental/out/_next/static/chunks/1a2lzi3ursud4.js:1
↓ 65 callersFunctiona
(_)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 65 callersMethodcall
(self, name: str, arguments: JsonRpc, server_id: str | None = None)
tests/integration/_support/mcp.py:723
↓ 65 callersFunctiondecoded_json_object
(value: object)
litellm/litellm_core_utils/core_helpers.py:144
↓ 65 callersMethoddelete_model
(self, model_id: str)
tests/e2e/batches/batch_client.py:156
↓ 65 callersMethodenqueue
(self, response: ResponseSpec)
tests/test_litellm_rust/support/recording_server.py:54
↓ 65 callersFunctionmake_spec
( *, token_url: str = "https://token.example/v1/oauth/token", assertion_ref: str = DEFAULT_REF,
tests/unit/llms/base_llm/auth/test_token_exchange.py:176
↓ 65 callersFunctionmessage_field
A message field, whether the message is a dict or a pydantic ``Message``. Clients replay assistant turns straight from a response, so a history m
litellm/litellm_core_utils/prompt_templates/mid_conversation_system.py:78
↓ 65 callersMethodoptional
()
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 65 callersFunctionpass_through_request
Pass through endpoint handler, makes the httpx request for pass-through endpoints and ensures logging hooks are called Args: request
litellm/proxy/pass_through_endpoints/pass_through_endpoints.py:1252
↓ 65 callersFunctionpost
(app: Router, path: &str, body: Value)
litellm-rust/crates/gateway-inference/tests/support/mod.rs:139
↓ 65 callersMethodprompt
(self)
tests/integration/providers/test_device_code_login_guard_wire.py:91
↓ 65 callersFunctionrecorded_spans
(url: str, since: int = 0)
tests/integration/_support/otlp_sink.py:336
↓ 65 callersMethodreject
(e,t={},r)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:14
↓ 65 callersFunctionupdate_team
Use `/team/member_add` AND `/team/member/delete` to add/remove new team members You can now update team budget / rate limits via /team/updat
litellm/proxy/management_endpoints/team_endpoints.py:2456
↓ 64 callersFunction_guardrail
(**overrides: object)
tests/unit/proxy/guardrails/guardrail_hooks/test_llm_shield_proxy.py:39
↓ 64 callersFunction_model_row
(model_id="m1", model_name="gpt-4o-mini-ptu", model_info=None, with_start=True)
tests/unit/proxy/spend_tracking/test_ptu_flat_cost_rollup.py:54
↓ 64 callersMethodabort
()
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:2
↓ 64 callersMethodbuild
(self)
litellm-rust/crates/router-core/src/lib.rs:275
↓ 64 callersFunctionempty
()
litellm-rust/crates/router-core/src/lookup.rs:762
↓ 64 callersFunctionensure_api_route
(api_base: str, route: str)
litellm/litellm_core_utils/url_utils.py:164
↓ 64 callersFunctionfailure_diagnostic
Build a human-readable error string from a non-zero `claude` CLI run. The CLI is annoying to debug because the most useful failure signal rar
tests/e2e/claude_code/cli_driver.py:577
↓ 64 callersMethodmodel_dump
(self)
tests/unit/repositories/test_repositories.py:58
↓ 64 callersMethodnames
(self, model_name: str | None = None, *, kind: str = "groups")
tests/unit/proxy/batches_endpoints/test_litellm_executed_batches.py:260
↓ 64 callersFunctionrequire_proxy
Return the proxy config (base URL + master key), or hard-fail the test. ``env`` is injected for tests; production callers pass nothing and
tests/e2e/claude_code/_env.py:62
↓ 64 callersFunctionroute_request
Common helper to route the request
litellm/proxy/route_llm_request.py:755
↓ 64 callersFunctionrr
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:5
↓ 64 callersMethodset_cache
(self, key: str | None, value: CacheValue, local_only: bool = False, **kwargs: object)
litellm/proxy/common_utils/user_api_key_cache.py:293
↓ 64 callersMethodstream
(self, path: str, body: dict[str, object] | None = None, *, key: str | None = None)
tests/integration/observability/test_presidio_streaming_output.py:168
↓ 64 callersMethodtransform_anthropic_messages_request
( self, model: str, messages: list[dict], anthropic_messages_optional_request_
litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude_transformation.py:769
↓ 64 callersFunctionuser_api_key_auth
Parent function to authenticate user api key / jwt token.
litellm/proxy/auth/user_api_key_auth.py:4604
↓ 63 callersFunction_mcp_data
(**overrides: Any)
tests/unit/proxy/guardrails/guardrail_hooks/test_agent_365.py:150
↓ 63 callersFunction_run
(guardrail: Agent365Guardrail, data: dict, call_type: str = "call_mcp_tool")
tests/unit/proxy/guardrails/guardrail_hooks/test_agent_365.py:166
↓ 63 callersMethodanthropic_messages
The proxy's ``/v1/messages`` route name for ``aanthropic_messages``; async.
litellm/router_rust/core.py:2589
↓ 63 callersFunctioncooled_down
(core: RouterCore, ids: list[str])
tests/unit/test_router/core/retries_health_helpers.py:105
← previousnext →601–700 of 202,479, ranked by callers