MCPcopy Create free account

hub / github.com/BerriAI/litellm / types & classes

Types & classes10,035 in github.com/BerriAI/litellm

↓ 2,306 callersClassUserAPIKeyAuth
Return the row in the db
litellm/proxy/_types.py:2420
↓ 664 callersClassError
litellm/proxy/_experimental/mcp_server/outbound_credentials/result.py:44
↓ 659 callersClassDualCache
DualCache is a cache implementation that updates both Redis and an in-memory cache simultaneously. When data is updated or inserted, it is wr
litellm/caching/dual_cache.py:51
↓ 647 callersClassRouter
litellm/router.py:239
↓ 567 callersClassModelResponse
litellm/types/utils.py:1835
↓ 419 callersClassUsage
litellm/types/utils.py:1521
↓ 366 callersClassGenericLiteLLMParams
LiteLLM Params without 'model' arg (used across completion / assistants api)
litellm/types/router.py:209
↓ 276 callersClassMCPServer
litellm/types/mcp_server/mcp_server_manager.py:24
↓ 262 callersClassMCPServerManager
litellm/proxy/_experimental/mcp_server/mcp_server_manager.py:499
↓ 260 callersClassChoices
litellm/types/utils.py:1367
↓ 250 callersClassMessage
litellm/types/utils.py:1142
↓ 228 callersClassRequest
tests/proxy_unit_tests/test_user_api_key_auth.py:31
↓ 209 callersClassLiteLLM_UserTable
litellm/models/user.py:20
↓ 207 callersClassProxyLogging
Logging/Custom Handlers for proxy. Implemented mainly to: - log successful/failed db read/writes - support the max parallel request
litellm/proxy/utils.py:397
↓ 204 callersClassOpenTelemetry
litellm/integrations/opentelemetry.py:302
↓ 197 callersClassHTTPHandler
litellm/llms/custom_httpx/http_handler.py:1066
↓ 186 callersClassAnthropicConfig
Reference: https://docs.anthropic.com/claude/reference/messages_post to pass metadata to anthropic, it's {"user_id": "any-relevant-informati
litellm/llms/anthropic/chat/transformation.py:235
↓ 185 callersClassLiteLLM_TeamTable
litellm/models/team.py:85
↓ 174 callersClassProxyException
litellm/proxy/_types.py:3199
↓ 170 callersClassDelta
litellm/types/utils.py:1260
↓ 163 callersClassProxyConfig
Abstraction class on top of config loading/updating logic. Gives us one place to control all config updating logic.
litellm/proxy/proxy_server.py:3465
↓ 161 callersClassAmazonConverseConfig
Reference - https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html #2 - https://docs.aws.amazon.com/bedrock/latest
litellm/llms/bedrock/chat/converse_transformation.py:103
↓ 160 callersClassModelResponseStream
litellm/types/utils.py:1763
↓ 154 callersClassStreamingChoices
litellm/types/utils.py:1670
↓ 130 callersClassNotImplementedError
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 126 callersClassProxyBaseLLMRequestProcessing
litellm/proxy/common_request_processing.py:784
↓ 121 callersClassLiteLLM_JWTAuth
A class to define the roles and permissions for a LiteLLM Proxy w/ JWT Auth. Attributes: - admin_jwt_scope: The JWT scope required for p
litellm/proxy/_types.py:4057
↓ 118 callersClassResponse
tests/test_litellm/router_utils/test_add_retry_fallback_headers.py:83
↓ 115 callersClassResponsesAPIResponse
litellm/types/llms/openai.py:1238
↓ 111 callersClassImageResponse
litellm/types/utils.py:2267
↓ 105 callersClassBaseAWSLLM
litellm/llms/bedrock/base_aws_llm.py:74
↓ 104 callersClassGenerateKeyRequest
litellm/proxy/_types.py:1090
↓ 104 callersClassJWTHandler
- treat the sub id passed in as the user id - return an error if id making request doesn't exist in proxy user table - track spend agains
litellm/proxy/auth/handle_jwt.py:77
↓ 104 callersClassLiteLLM_Params
LiteLLM Params with 'model' requirement - used for completions
litellm/types/router.py:317
↓ 104 callersClassLiteLLM_VerificationToken
litellm/models/verification_token.py:17
↓ 103 callersClassFunction
litellm/types/utils.py:984
↓ 103 callersClassMember
litellm/models/team.py:39
↓ 103 callersClassPromptTokensDetailsWrapper
litellm/types/utils.py:1460
↓ 99 callersClassGenericGuardrailAPIInputs
litellm/types/utils.py:3721
↓ 96 callersClassInternalUsageCache
litellm/proxy/utils.py:224
↓ 94 callersClassVertexGeminiConfig
Reference: https://cloud.google.com/vertex-ai/docs/generative-ai/chat/test-chat-prompts Reference: https://cloud.google.com/vertex-ai/generat
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:171
↓ 93 callersClassCustomStreamWrapper
litellm/litellm_core_utils/streaming_handler.py:114
↓ 92 callersClassCache
litellm/caching/caching.py:55
↓ 92 callersClassEmbeddingResponse
litellm/types/utils.py:1952
↓ 86 callersClassAsyncHTTPHandler
litellm/llms/custom_httpx/http_handler.py:509
↓ 85 callersClassDeployment
litellm/types/router.py:432
↓ 84 callersClassOCIChatConfig
LiteLLM BaseConfig implementation for OCI Generative AI chat.
litellm/llms/oci/chat/transformation.py:255
↓ 79 callersClassLiteLLMAnthropicMessagesAdapter
litellm/llms/anthropic/experimental_pass_through/adapters/transformation.py:257
↓ 75 callersClassOpenTelemetryConfig
litellm/integrations/opentelemetry.py:217
↓ 73 callersClassImageObject
Represents the url or the content of an image generated by the OpenAI API. Attributes: b64_json: The base64-encoded JSON of the generate
litellm/types/utils.py:2188
↓ 73 callersClassRedisCache
litellm/caching/redis_cache.py:193
↓ 71 callersClass_OPTIONAL_PresidioPIIMasking
litellm/proxy/guardrails/guardrail_hooks/presidio.py:66
↓ 70 callersClassOk
litellm/proxy/_experimental/mcp_server/outbound_credentials/result.py:33
↓ 70 callersClassRealTimeStreaming
litellm/litellm_core_utils/realtime_streaming.py:46
↓ 70 callersClassTeamRepository
Repository for team database operations.
litellm/repositories/team_repository.py:13
↓ 69 callersClassBedrockGuardrail
litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py:142
↓ 68 callersClassContentFilterGuardrail
Content filter guardrail that detects sensitive information using: - Prebuilt regex patterns (SSN, credit cards, API keys, etc.) - Custom
litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/content_filter.py:129
↓ 68 callersClassLiteLLM_BudgetTable
Represents user-controllable params for a LiteLLM_BudgetTable record. Budget-write paths use `model_fields.keys()` on this class as an allowlist
litellm/models/budget.py:16
↓ 67 callersClassChatCompletionMessageToolCall
litellm/types/utils.py:1052
↓ 67 callersClassUpdateKeyRequest
litellm/proxy/_types.py:1146
↓ 65 callersClassUserRepository
Repository for user database operations.
litellm/repositories/user_repository.py:12
↓ 64 callersClassVertexBase
litellm/llms/vertex_ai/vertex_llm_base.py:39
↓ 62 callersClassAmazonAnthropicClaudeMessagesConfig
Call Claude model family in the /v1/messages API spec Supports anthropic_beta parameter for beta features.
litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py:69
↓ 61 callersClassHeaders
Base for header models. Subclasses may alias to hyphenated header names (e.g. ``x-litellm-api-key``); serialization uses by_alias.
tests/e2e/e2e_http.py:22
↓ 61 callersClass_PROXY_MaxParallelRequestsHandler
litellm/proxy/hooks/parallel_request_limiter.py:44
↓ 60 callersClassCustomGuardrail
litellm/integrations/custom_guardrail.py:81
↓ 58 callersClassFakeHandler
tests/test_litellm/proxy/guardrails/guardrail_hooks/test_vigil_guard.py:38
↓ 58 callersClassLiteLLM_TeamTableCachedObj
litellm/models/team.py:135
↓ 57 callersClassInMemoryCache
litellm/caching/in_memory_cache.py:27
↓ 57 callersClassWebSearchInterceptionLogger
CustomLogger that intercepts WebSearch tool calls for models that don't natively support web search. Implements agentic loop: 1. Det
litellm/integrations/websearch_interception/handler.py:52
↓ 55 callersClassGenAIHubOrchestrationConfig
litellm/llms/sap/chat/transformation.py:108
↓ 55 callersClassOAuthToken
A user's OAuth credential: the bearer value, when it expires, and how to refresh it. ``expires_at`` is epoch seconds (``None`` means no known exp
litellm/proxy/_experimental/mcp_server/outbound_credentials/oauth_token_store.py:25
↓ 55 callersClassPrismaClient
litellm/proxy/utils.py:2778
↓ 54 callersClassBaseLLMHTTPHandler
litellm/llms/custom_httpx/llm_http_handler.py:231
↓ 54 callersClassCompletionTokensDetailsWrapper
litellm/types/utils.py:1444
↓ 54 callersClassModelInfo
litellm/types/router.py:124
↓ 54 callersClassNewTeamRequest
litellm/proxy/_types.py:1694
↓ 54 callersClassOpenTelemetryV2Config
litellm/integrations/otel/model/config.py:103
↓ 52 callersClassLitellmParams
litellm/types/guardrails.py:787
↓ 52 callersClassStandardLoggingPayload
litellm/types/utils.py:2857
↓ 52 callersClassTranscriptionResponse
litellm/types/utils.py:2366
↓ 52 callersClass_PROXY_LiteLLMManagedFiles
enterprise/litellm_enterprise/proxy/hooks/managed_files.py:76
↓ 51 callersClassLiteLLM_ObjectPermissionTable
Represents a LiteLLM_ObjectPermissionTable record
litellm/models/object_permission.py:13
↓ 51 callersClassLogging
litellm/litellm_core_utils/litellm_logging.py:289
↓ 50 callersClassLlmProviders
litellm/types/utils.py:3225
↓ 50 callersClassRerankResponse
litellm/types/rerank.py:65
↓ 50 callersClassVerificationTokenRepository
Repository for verification token (API key) database operations.
litellm/repositories/verification_token_repository.py:15
↓ 49 callersClassGeminiRealtimeConfig
litellm/llms/gemini/realtime/transformation.py:75
↓ 44 callersClassBedrockError
litellm/llms/bedrock/common_utils.py:44
↓ 44 callersClassCallInfo
Used for slack budget alerting
litellm/proxy/_types.py:2833
↓ 44 callersClassDataDogLogger
litellm/integrations/datadog/datadog.py:88
↓ 44 callersClassLassoGuardrail
Lasso Security Guardrail integration for LiteLLM. Provides content moderation, PII detection, and policy enforcement through the Lasso S
litellm/proxy/guardrails/guardrail_hooks/lasso/lasso.py:88
↓ 44 callersClassProxyRateLimitError
A 429 raised by litellm's proxy-side rate limiting hooks. This class deliberately inherits from BOTH :class:`litellm.exceptions.RateLimi
litellm/proxy/common_utils/proxy_rate_limit_error.py:100
↓ 44 callersClassStandardCallbackDynamicParams
litellm/types/utils.py:2928
↓ 44 callersClassUserAPIKeyLabelValues
Prometheus metric label inputs (Python field names match historical Pydantic ``model_dump`` keys). Immutable value object: use ``dataclasses
litellm/types/integrations/prometheus.py:794
↓ 43 callersClassBedrockMantleResponsesAPIConfig
litellm/llms/bedrock_mantle/responses/transformation.py:46
↓ 43 callersClassCodeInterpreterInterceptionLogger
CustomLogger that implements transparent code-interpreter execution loops. Flow: 1. Replace the native ``code_interpreter`` tool with a
litellm/integrations/code_interpreter_interception/handler.py:118
↓ 43 callersClassLiteLLMBatch
litellm/types/utils.py:3503
↓ 43 callersClassNewMCPServerRequest
litellm/proxy/_types.py:1221
↓ 43 callersClassOpenAIVideoConfig
Configuration class for OpenAI video generation.
litellm/llms/openai/videos/transformation.py:39
next →1–100 of 10,035, ranked by callers