MCPcopy Create free account

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

Types & classes26,341 in github.com/BerriAI/litellm

↓ 5,741 callersClassUserAPIKeyAuth
Return the row in the db
litellm/types/proxy/auth/user_api_key_auth.py:129
↓ 1,765 callersClassOk
litellm/proxy/mcp_server/outbound_credentials/result.py:33
↓ 1,713 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:70
↓ 1,540 callersClassReply
tests/integration/_support/wire.py:66
↓ 1,445 callersClassRouter
What type checkers see: the constructor's parameters and the endpoints' return types. The endpoints are served by the core at run time (litell
litellm/router.py:244
↓ 1,055 callersClassPath
litellm-rust/crates/gateway-mcp/src/request.rs:33
↓ 1,033 callersClassModelResponse
litellm/types/utils.py:2402
↓ 982 callersClassUsage
litellm/types/utils.py:2035
↓ 803 callersClassMCPServer
litellm/types/mcp_server/mcp_server_manager.py:96
↓ 792 callersClassError
litellm/proxy/mcp_server/outbound_credentials/result.py:44
↓ 760 callersClassField
litellm-rust/crates/python-bridge/src/coercion.rs:82
↓ 723 callersClassGenericLiteLLMParams
LiteLLM Params without 'model' arg (used across completion / assistants api)
litellm/types/router.py:583
↓ 709 callersClassMCPServerManager
litellm/proxy/mcp_server/mcp_server_manager.py:1909
↓ 507 callersClassLiteLLM_UserTable
litellm/models/user.py:19
↓ 487 callersClassAsyncHTTPHandler
litellm/llms/custom_httpx/http_handler.py:717
↓ 465 callersClassRequest
tests/unit/proxy/auth/test_user_api_key_auth.py:29
↓ 460 callersClassLiteLLM_TeamTable
litellm/models/team.py:86
↓ 433 callersClassProxyLogging
Logging/Custom Handlers for proxy. Implemented mainly to: - log successful/failed db read/writes - support the max parallel request
litellm/proxy/utils.py:1958
↓ 430 callersClassHTTPHandler
litellm/llms/custom_httpx/http_handler.py:1565
↓ 430 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:5930
↓ 425 callersClassRoutingContext
What a routing plugin (strategy, pre-call check, sub-router) may use of the router. Plugins get one instead of the Router itself.
litellm/router_api.py:1530
↓ 419 callersClassChoices
litellm/types/utils.py:1795
↓ 416 callersClassDelta
litellm/types/utils.py:1658
↓ 396 callersClassNumber
litellm-rust/crates/cost/src/money.rs:94
↓ 392 callersClassMessage
litellm/types/utils.py:1537
↓ 373 callersClassResponse
tests/unit/router_utils/test_add_retry_fallback_headers.py:232
↓ 371 callersClassModelResponseStream
litellm/types/utils.py:2310
↓ 369 callersClassUserApiKeyCache
DualCache for UserAPIKeyAuth-like payloads. Stores a Redis-safe JSON payload in memory and, with ``enable_redis_auth_cache``, in Redis, to a
litellm/proxy/common_utils/user_api_key_cache.py:50
↓ 338 callersClassStreamingChoices
litellm/types/utils.py:2198
↓ 324 callersClassLiteLLM_Params
LiteLLM Params with 'model' requirement - used for completions
litellm/types/router.py:762
↓ 323 callersClassInternalUsageCache
litellm/proxy/utils.py:496
↓ 306 callersClassDeployment
litellm/types/router.py:903
↓ 295 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:593
↓ 293 callersClassProxyException
litellm/proxy/_types.py:3907
↓ 281 callersClassLogging
litellm/litellm_core_utils/litellm_logging.py:713
↓ 280 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:222
↓ 271 callersClassGenericGuardrailAPIInputs
litellm/types/utils.py:5378
↓ 248 callersClassComplexityRouter
Complexity router that classifies requests and routes to appropriate models. By default, handles requests in <1ms with zero external API cal
litellm/router_strategy/complexity_router/complexity_router.py:1417
↓ 246 callersClassModelInfo
litellm/types/router.py:293
↓ 243 callersClassOpenTelemetry
litellm/integrations/opentelemetry.py:442
↓ 235 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:4938
↓ 235 callersClassResponsesAPIResponse
litellm/types/llms/openai.py:1578
↓ 233 callersClassMember
tests/integration/authorization/test_team_member_permissions.py:80
↓ 232 callersClassLiteLLM_ObjectPermissionTable
Represents a LiteLLM_ObjectPermissionTable record
litellm/models/object_permission.py:11
↓ 218 callersClassProxyBaseLLMRequestProcessing
litellm/proxy/common_request_processing.py:2343
↓ 217 callersClassPromptTokensDetailsWrapper
litellm/types/utils.py:1901
↓ 212 callersClassInMemoryCache
litellm/caching/in_memory_cache.py:31
↓ 211 callersClassLiteLLMParamsBody
POST /model/new litellm_params: `model` is the only required field; `api_key` et al may be an `os.environ/FOO` reference the proxy resolves at cal
tests/e2e/models.py:1354
↓ 206 callersClassLiteLLM_VerificationToken
litellm/models/verification_token.py:16
↓ 199 callersClassOpenAIResponsesHandler
Handler for processing OpenAI Responses API with guardrails. This class provides methods to: 1. Process input (pre-call hook) 2. Pro
litellm/llms/openai/responses/guardrail_translation/handler.py:767
↓ 192 callersClassUpdateKeyRequest
litellm/types/proxy/management_endpoints/key_requests.py:104
↓ 192 callersClass_PROXY_MaxParallelRequestsHandler
litellm/proxy/hooks/parallel_request_limiter.py:78
↓ 191 callersClassCustomStreamWrapper
litellm/litellm_core_utils/streaming_handler.py:409
↓ 183 callersClassChangeSet
Runtime changes for ``apply``. Applied in this order: ``assign``, ``settings``, ``upsert``, ``delete``, ``redis_cache``. - ``assign``: r
litellm/router_api.py:1420
↓ 182 callersClassLiteLLMAnthropicMessagesAdapter
litellm/llms/anthropic/messages/adapters/transformation.py:485
↓ 177 callersClassImageResponse
litellm/types/utils.py:2847
↓ 175 callersClassGenerateKeyRequest
litellm/types/proxy/management_endpoints/key_requests.py:75
↓ 171 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:734
↓ 168 callersClassOpenTelemetryV2Config
litellm/integrations/otel/model/config.py:148
↓ 163 callersClassMCPTool
litellm/types/mcp_server/tool_registry.py:9
↓ 160 callersClassDBSpendUpdateWriter
Module responsible for 1. Writing spend increments to either in memory list of transactions or to redis 2. Reading increments from redis
litellm/proxy/db/db_spend_update_writer.py:675
↓ 160 callersClassFunction
litellm/types/utils.py:1330
↓ 159 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:233
↓ 156 callersClassBaseLLMHTTPHandler
litellm/llms/custom_httpx/llm_http_handler.py:711
↓ 151 callersClassBedrockGuardrail
litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py:276
↓ 150 callersClassNotImplementedError
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 148 callersClassBaseAWSLLM
litellm/llms/bedrock/base_aws_llm.py:157
↓ 148 callersClassEmbeddingResponse
litellm/types/utils.py:2515
↓ 147 callersClassCache
litellm/caching/caching.py:128
↓ 147 callersClassLitellmParams
litellm/types/guardrails.py:1401
↓ 147 callersClassupdateDeployment
litellm/types/router.py:801
↓ 145 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
↓ 140 callersClassObject
litellm-rust/crates/config/src/value.rs:10
↓ 138 callersClassChatMessage
tests/e2e/models.py:232
↓ 134 callersClassS3Logger
litellm/integrations/s3_v2.py:157
↓ 132 callersClassRealTimeStreaming
litellm/litellm_core_utils/realtime_streaming.py:485
↓ 131 callersClassPrometheusLogger
litellm/integrations/prometheus.py:493
↓ 130 callersClassCredentialItem
litellm/models/credentials.py:25
↓ 125 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:33
↓ 124 callersClassAnthropicMessagesHandler
Process Anthropic messages with guardrails. In-sequence system entries are untrusted client input. This handler scans and preserves them thro
litellm/llms/anthropic/chat/guardrail_translation/handler.py:577
↓ 121 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:341
↓ 118 callersClassCustomGuardrail
litellm/integrations/custom_guardrail.py:389
↓ 117 callersClassLiteLLM_TeamTableCachedObj
litellm/models/team.py:136
↓ 116 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_claude_transformation.py:89
↓ 115 callersClassLiteLLMResponsesTransformationHandler
Handler for transforming /chat/completions api requests to litellm.responses requests
litellm/completion_extras/litellm_responses_transformation/transformation.py:883
↓ 112 callersClassUpdateTeamRequest
UpdateTeamRequest, used by /team/update when you need to update a team team_id: str team_alias: Optional[str] = None organization_id
litellm/proxy/_types.py:1985
↓ 112 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:266
↓ 110 callersClassUnifiedLLMGuardrails
litellm/proxy/guardrails/guardrail_hooks/unified_guardrail/unified_guardrail.py:247
↓ 108 callersClassChatBody
tests/e2e/models.py:350
↓ 108 callersClassTextContent
litellm/types/interactions/generated.py:378
↓ 106 callersClassChatCompletionMessageToolCall
litellm/types/utils.py:1435
↓ 105 callersClassVertexBase
litellm/llms/vertex_ai/vertex_llm_base.py:105
↓ 101 callersClassAgentResponse
litellm/types/agents.py:314
↓ 101 callersClassBedrockFilesConfig
Config for Bedrock Files - handles S3 uploads for Bedrock batch processing
litellm/llms/bedrock/files/transformation.py:590
↓ 99 callersClassLiteLLM_MCPServerTable
Represents a LiteLLM_MCPServerTable record
litellm/models/mcp_server.py:49
↓ 99 callersStructModelResponse
ModelResponse represents a response from the API containing model information.
terraform/provider/litellm/types.go:21
↓ 98 callersClassAnthropicStreamWrapper
- first chunk return 'message_start' - content block must be started and stopped - finish_reason must map exactly to anthropic reason, el
litellm/llms/anthropic/messages/adapters/streaming_iterator.py:623
↓ 98 callersClassBedrockError
litellm/llms/bedrock/common_utils.py:108
↓ 98 callersClassFireworksAIConfig
Reference: https://docs.fireworks.ai/api-reference/post-chatcompletions The class `FireworksAIConfig` provides configuration for the Firewor
litellm/llms/fireworks_ai/chat/transformation.py:161
↓ 97 callersClassBedrockRealtimeConfig
Configuration for Bedrock Nova Sonic realtime transformations.
litellm/llms/bedrock/realtime/transformation.py:211
next →1–100 of 26,341, ranked by callers