MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 5 callersFunction_chat
(gateway: Gateway, stream: tuple[bytes, ...])
tests/integration/streaming/test_responses_top_level_error_events.py:64
↓ 5 callersFunction_chat
(proxy: Gateway, model: str, key: str)
tests/integration/management/test_user_rate_limit_updates.py:54
↓ 5 callersFunction_chat_answer
(proxy: Gateway, alias: str)
tests/integration/configuration/test_effective_settings.py:1180
↓ 5 callersFunction_chat_body
(model: str, text: str, *, stream: bool = False)
tests/integration/compatibility/test_compressed_request_bodies.py:229
↓ 5 callersFunction_chat_completion
()
tests/integration/sdk/test_openai_sdk_client_sessions_wire.py:50
↓ 5 callersFunction_chat_completion_reply
()
tests/unit/llms/mistral/test_mistral_chat_transformation.py:1917
↓ 5 callersFunction_chat_content
(text: str)
tests/integration/providers/test_custom_prompt_template_wire.py:179
↓ 5 callersFunction_chat_function_call_item
(call_id="call_1", name=LITELLM_CODE_EXECUTION_TOOL_NAME)
tests/unit/integrations/code_interpreter_interception/test_handler.py:90
↓ 5 callersFunction_chat_response
(usage: dict[str, object])
tests/unit/llms/clf_ai_gateway/test_clf_ai_gateway_chat_transformation.py:18
↓ 5 callersFunction_chat_text
(chunks: Iterable[dict[str, JsonValue]])
tests/integration/providers/test_bedrock_converse_stream_event_frames_wire.py:246
↓ 5 callersFunction_chat_text
(chunks: list[dict[str, JsonValue]])
tests/integration/streaming/test_openai_like_stream_usage_wire.py:125
↓ 5 callersFunction_chat_text
(chunks: List[Any])
tests/unit/proxy/guardrails/guardrail_hooks/unified_guardrails/test_streaming_buffer_until_moderated.py:408
↓ 5 callersFunction_chat_with_headers
(proxy: ProxyClient, headers: AuthHeaders | NoBody)
tests/e2e/access_control/test_chat_auth_headers_e2e.py:22
↓ 5 callersFunction_check
(guardrail: GenericGuardrailAPI)
tests/unit/proxy/guardrails/guardrail_hooks/test_generic_guardrail_api.py:2518
↓ 5 callersFunction_check_caller_models
( agent_key: UserAPIKeyAuth, model: str, load_team: CallerTeamLoader, load_user: CallerUserLoa
tests/unit/proxy/auth/test_auth_checks_object_access_and_lookup.py:11461
↓ 5 callersFunction_check_key_project_team_on_mutation
( data: UpdateKeyRequest | RegenerateKeyRequest, existing_key_row: LiteLLM_VerificationToken, pris
litellm/proxy/management_endpoints/key_management_endpoints.py:2164
↓ 5 callersMethod_check_open
(self)
litellm/harness/sandbox/local.py:150
↓ 5 callersMethod_check_patterns
Check text against all compiled regex patterns. Args: text: Text to check Returns: Tuple of (matche
litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/content_filter.py:1068
↓ 5 callersFunction_check_project_key_limits
Validate that key's models and budget respect its project's limits. - Key models must be a subset of project models, except the all-team-mod
litellm/proxy/management_endpoints/key_management_endpoints.py:2035
↓ 5 callersFunction_check_user_exists
Check if user exists and return user, raise 404 if not found.
litellm/proxy/management_endpoints/scim/scim_v2.py:312
↓ 5 callersFunction_check_user_model_budget
Enforce the internal user's own `model_max_budget` across the request's models. Separate from the key check: a user's per-model budget caps every
litellm/proxy/auth/user_api_key_auth.py:548
↓ 5 callersFunction_check_wildcard_routing
Returns True if a model is a provider wildcard. eg: - anthropic/* - openai/* - *
litellm/proxy/auth/model_checks.py:61
↓ 5 callersFunction_chunk
(identity: str, **fields)
tests/unit/proxy/pass_through_endpoints/test_injected_stream_usage.py:19
↓ 5 callersFunction_chunked
(payload: bytes, size: int)
tests/unit/llms/anthropic/messages/native/test_streaming_iterator.py:1729
↓ 5 callersFunction_chunks
(payload: bytes, size: int)
tests/unit/proxy/pass_through_endpoints/test_managed_id_rewriter.py:69
↓ 5 callersFunction_chunks
()
tests/unit/llms/bedrock/chat/test_invoke_handler.py:1007
↓ 5 callersFunction_classifier_failure_reason
(exc: Exception)
litellm/router_strategy/complexity_router/complexity_router.py:1332
↓ 5 callersMethod_classify_batch_record
Decide which OpenAI endpoint shape an OpenAI batch JSONL line carries. Precedence (strict - any recognized `url` short-circuits):
litellm/llms/bedrock/files/transformation.py:761
↓ 5 callersFunction_claude_code_turn
(system_output_config)
tests/unit/llms/anthropic/messages/native/test_anthropic_messages_per_turn_control.py:21
↓ 5 callersMethod_clear_sso_env
(self, monkeypatch)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:1150
↓ 5 callersFunction_cli_bearer_headers
(key: str)
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_gateway_wire.py:67
↓ 5 callersFunction_cli_callback_user_info
(teams)
tests/unit/proxy/management_endpoints/test_ui_sso.py:10548
↓ 5 callersFunction_client
(endpoint: ModelEndpoint)
tests/integration/providers/test_audit_any_sweep_harness_endpoint.py:25
↓ 5 callersFunction_client
(gateway: Gateway, key: str)
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_count_tokens_wire.py:38
↓ 5 callersFunction_client
(text: str)
tests/unit/test_ws_vcr.py:44
↓ 5 callersFunction_client
(endpoint: _MantleEndpoint)
tests/unit/llms/bedrock/count_tokens/test_bedrock_mantle_count_tokens_handler.py:42
↓ 5 callersFunction_client
(transport: _HeaderCapturingTransport, path: str, is_async: bool)
tests/unit/llms/base_llm/chat/test_attribution_headers.py:71
↓ 5 callersMethod_client_blocks
(self, chunks: list[bytes])
tests/unit/proxy/guardrails/guardrail_hooks/test_tool_permission.py:3744
↓ 5 callersFunction_client_for_aim
(guardrail: AimGuardrail)
tests/unit/proxy/guardrails/guardrail_hooks/test_aim.py:33
↓ 5 callersFunction_client_for_role
(role: LitellmUserRoles)
tests/unit/proxy/a2a/test_discovery.py:213
↓ 5 callersFunction_client_job
(job_id: str, status: str, file_id: str)
tests/integration/security/test_fine_tuning_managed_ids.py:81
↓ 5 callersFunction_client_raising_4xx
An httpx client whose POST returns a 4xx whose ``raise_for_status`` raises an HTTPStatusError carrying ``body`` as its JSON, so the RFC 6749 error
tests/unit/proxy/mcp_server/outbound_credentials/test_token_exchange_provider.py:24
↓ 5 callersMethod_client_request
(model: str)
tests/unit/proxy/test_common_request_processing.py:8962
↓ 5 callersFunction_client_stream
( message: dict[str, JsonValue], replay: Literal["async", "sync"] )
tests/unit/litellm_core_utils/llm_response_utils/test_convert_to_streaming_response.py:462
↓ 5 callersFunction_clients
(stack: ExitStack, base_url: str, count: int, timeout: float = 30)
tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py:352
↓ 5 callersMethod_clone_request_data
(request_data: dict)
tests/unit/proxy/guardrails/guardrail_hooks/test_noma.py:216
↓ 5 callersMethod_clone_user_auth
(user_auth: UserAPIKeyAuth)
tests/unit/proxy/guardrails/guardrail_hooks/test_noma.py:212
↓ 5 callersFunction_close
(tag: str)
litellm/llms/bedrock/count_tokens/kimi_k3.py:298
↓ 5 callersMethod_close_recycled_session
Deterministically dispose a ClientSession this transport is replacing. Covers the three lifecycles a recycled session can be in: - it
litellm/llms/custom_httpx/aiohttp_transport.py:277
↓ 5 callersFunction_codes
(path_name, triggers)
tests/unit/test_assert_workflow_dir_hygiene.py:18
↓ 5 callersFunction_cold_storage_key
(request_id: str, database_url: str | None = None)
tests/integration/observability/test_s3_v2_partition_granularity.py:175
↓ 5 callersFunction_collect
(stream: AsyncIterator[bytes])
tests/unit/proxy/pass_through_endpoints/test_managed_id_rewriter.py:74
↓ 5 callersFunction_collect
(stream)
tests/unit/harness/test_runtime.py:53
↓ 5 callersFunction_collect_cache_points
(result)
tests/unit/llms/bedrock/chat/test_converse_transformation.py:8448
↓ 5 callersMethod_commit
(self, value: object)
litellm/router_rust/surface/indexes.py:294
↓ 5 callersFunction_comparison_body
(response_id: str, nested: bool)
tests/integration/authorization/test_responses_id_ownership.py:135
↓ 5 callersFunction_complete
(sync_mode: bool, stream: bool, **kwargs)
tests/unit/llms/vertex_ai/context_caching/test_known_cached_contents.py:441
↓ 5 callersMethod_completed
(sequence_number, output)
tests/unit/llms/openai/responses/test_openai_responses_guardrail_handler.py:4940
↓ 5 callersFunction_completed_batch
()
tests/unit/proxy/openai_files_endpoint/test_files_common_utils.py:197
↓ 5 callersFunction_completed_batch_for_retire
(output_file_id: str | None, counts: BatchRequestCounts | None = None)
tests/unit/proxy/openai_files_endpoint/test_files_common_utils.py:407
↓ 5 callersFunction_completed_codex_upstream
(output_text: str, incomplete_reason: str | None = None)
tests/unit/llms/chatgpt/responses/test_chatgpt_responses_transformation.py:631
↓ 5 callersFunction_completion_chunk
(text: str, finish_reason: str | None, **choice_extras: object)
tests/unit/text_completions/test_streaming_iterator.py:92
↓ 5 callersFunction_compute_daily_flat_cost
Flat cost for ``day``: ptu_count * cost_per_ptu_per_hour * active_hours.
litellm/proxy/spend_tracking/ptu_flat_cost_rollup.py:238
↓ 5 callersFunction_compute_overall_action
Return the worst-case action: blocked > masked > error > unsupported > passed.
litellm/proxy/management_endpoints/policy_endpoints/endpoints.py:1303
↓ 5 callersFunction_config
(license_id: str | None = "org-1")
tests/unit/proxy/enterprise_billing/test_billing_metrics.py:58
↓ 5 callersFunction_config_prisma
Build an AsyncMock prisma client whose litellm_config returns `record`.
tests/unit/proxy/management_endpoints/test_credential_migration.py:136
↓ 5 callersFunction_config_table
(prisma_client: PrismaClient)
litellm/proxy/common_utils/periodic_reload_schedule.py:66
↓ 5 callersFunction_config_with
(authenticator: MagicMock)
tests/unit/llms/chatgpt/responses/test_chatgpt_responses_transformation.py:448
↓ 5 callersFunction_configuration_identity
(server: MCPServer)
litellm/proxy/mcp_server/catalog.py:64
↓ 5 callersFunction_configure_manager
(monkeypatch: pytest.MonkeyPatch, fixture: ParityFixture)
tests/unit/secret_managers/test_cyberark_secret_manager.py:42
↓ 5 callersFunction_configured
(path: str, name: str)
tests/unit/proxy/test_route_priority.py:51
↓ 5 callersFunction_configured
(make_core: MakeCore)
tests/unit/test_router/core/test_deprecated_members.py:112
↓ 5 callersFunction_configured_model_info
(deployment: Mapping[str, object])
litellm/router_rust/surface/model_info.py:143
↓ 5 callersFunction_conflict_row
(server_id: str = "other-server")
tests/unit/proxy/mcp_server/test_mcp_partial_update.py:933
↓ 5 callersFunction_conftest_codes
(tmp_path, source, name="conftest.py")
tests/unit/test_check_test_quality.py:424
↓ 5 callersFunction_constant_listing
(store: str, *file_ids: JsonValue)
tests/integration/management/test_vector_store_file_list_managed_ids.py:150
↓ 5 callersMethod_construct_url
Construct the backend websocket URL with the client's query parameters. `model` is left out for `intent=transcription` on OpenAI's o
litellm/llms/openai/realtime/handler.py:144
↓ 5 callersFunction_contents
(marker: str)
tests/integration/providers/test_google_genai_adapter_wire.py:257
↓ 5 callersFunction_converse_messages
( messages: list[dict[str, object]], model: str, base_model: str | None, use_async: bool,
tests/unit/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py:1083
↓ 5 callersFunction_converse_peer
(reasoning: str)
tests/integration/streaming/test_fake_stream_reasoning_wire.py:199
↓ 5 callersFunction_converse_tool_call_reply
(sent: list[httpx.Request])
tests/unit/llms/bedrock/chat/test_converse_transformation.py:9688
↓ 5 callersFunction_convert
(messages: Sequence[Message])
tests/unit/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py:1628
↓ 5 callersFunction_convert_detail_to_media_resolution_enum
( detail: str | None, )
litellm/llms/vertex_ai/gemini/transformation.py:123
↓ 5 callersMethod_convert_grounding_metadata_to_annotations
Convert Vertex AI grounding metadata to OpenAI-style annotations.
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:2951
↓ 5 callersMethod_convert_messages_to_api_format
Convert LiteLLM messages to Qualifire API format. Supports tool calls for tool_selection_quality_check. Returns a list of di
litellm/proxy/guardrails/guardrail_hooks/qualifire/qualifire.py:147
↓ 5 callersMethod_convert_tools_to_functions
Convert OpenAI tools format to GigaChat functions format.
litellm/llms/gigachat/chat/transformation.py:233
↓ 5 callersMethod_cookie
(resp)
tests/unit/proxy/management_endpoints/test_ui_sso.py:11006
↓ 5 callersFunction_coordination_failure
(database_url: str, exc: "psycopg.Error", *, connecting: bool)
litellm-proxy-extras/litellm_proxy_extras/migration_lock.py:74
↓ 5 callersFunction_core_class
()
litellm/router.py:289
↓ 5 callersMethod_core_has_model_id
(self, candidate_id: str)
litellm/router_rust/surface/registry.py:1544
↓ 5 callersFunction_cost
(response, provider)
tests/unit/llms/nadir/test_nadir.py:48
↓ 5 callersFunction_cost_map_model
(key: str, entry: Mapping[str, object])
tests/unit/test_router/test_router.py:1907
↓ 5 callersFunction_cost_upserts
usage_unit -> (cost, untracked_units) written on create; the update path must increment by the same.
tests/unit/proxy/guardrails/test_usage_tracking.py:68
↓ 5 callersFunction_count_body
(rig: _Rig, marker: str, **fields: JsonValue)
tests/integration/providers/test_malformed_tools_wire.py:752
↓ 5 callersFunction_count_peer
( expected_body: dict[str, JsonValue], result: Reply, expected_beta: str = _COUNT_BETA )
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_count_tokens_wire.py:47
↓ 5 callersFunction_counted_contents
(count_body: Mapping[str, JsonValue])
tests/integration/providers/test_vertex_gemini_count_tokens_wire.py:232
↓ 5 callersFunction_counter
(internal_usage_cache, rate_limiter, descriptor_key, value, rate_limit_type)
tests/unit/proxy/hooks/test_batch_rate_limiter.py:51
↓ 5 callersMethod_counter_key
(scope: BatchEnqueuedTokenScope)
litellm/proxy/hooks/batch_enqueued_tokens.py:221
↓ 5 callersFunction_counter_mgets
(router: Router, client: FakeClient, redis_cache: FakeRedisCache)
tests/unit/caching/test_request_redis_batch_pre_call.py:351
↓ 5 callersFunction_create
(gateway: Gateway, body: Mapping[str, JsonValue])
tests/integration/providers/test_dashscope_video_chaos.py:91
← previousnext →14,101–14,200 of 202,479, ranked by callers