Skip to main content
Google Cloud Documentation
Technology areas
  • AI and ML
  • Application development
  • Application hosting
  • Compute
  • Data analytics and pipelines
  • Databases
  • Distributed, hybrid, and multicloud
  • Generative AI
  • Industry solutions
  • Networking
  • Observability and monitoring
  • Security
  • Storage
Cross-product tools
  • Access and resources management
  • Costs and usage management
  • Infrastructure as code
  • Migration
  • SDK, languages, frameworks, and tools
/
Console
  • English
  • Deutsch
  • Español – América Latina
  • Français
  • Português – Brasil
  • 中文 – 简体
  • 日本語
  • 한국어
Sign in
  • Vertex AI
  • Generative AI on Vertex AI
Start free
Guides API reference Vertex AI Cookbook Prompt gallery Resources FAQ Pricing
Google Cloud Documentation
  • Technology areas
    • More
    • Guides
    • API reference
    • Vertex AI Cookbook
    • Prompt gallery
    • Resources
    • FAQ
    • Pricing
  • Cross-product tools
    • More
  • Console
  • REST and RPC reference
  • Vertex AI in express mode
    • REST API reference
    • v1
      • Overview
      • countTokens
      • generateContent
      • streamGenerateContent
    • v1beta1
      • Overview
      • countTokens
      • generateContent
      • streamGenerateContent
  • REST
    • All methods
    • v1
      • REST Resources
      • media
        • Overview
        • upload
      • projects
        • Overview
        • getCacheConfig
        • updateCacheConfig
      • projects.locations
        • Overview
        • augmentPrompt
        • corroborateContent
        • evaluateDataset
        • evaluateInstances
        • generateInstanceRubrics
        • generateSyntheticData
        • getRagEngineConfig
        • retrieveContexts
        • updateRagEngineConfig
      • projects.locations.batchPredictionJobs
        • Overview
        • cancel
        • create
        • delete
        • get
        • list
      • projects.locations.cachedContents
        • Overview
        • create
        • delete
        • get
        • list
        • patch
      • projects.locations.endpoints
        • Overview
        • computeTokens
        • countTokens
        • fetchPredictOperation
        • generateContent
        • predict
        • predictLongRunning
        • rawPredict
        • serverStreamingPredict
        • streamGenerateContent
        • streamRawPredict
      • projects.locations.endpoints.chat
        • Overview
        • completions
      • projects.locations.endpoints.deployedModels.invoke
        • Overview
        • invoke
      • projects.locations.endpoints.google.science
        • Overview
        • inference
      • projects.locations.endpoints.invoke
        • Overview
        • invoke
      • projects.locations.endpoints.openapi
        • Overview
        • embeddings
      • projects.locations.evaluationItems
        • Overview
        • create
        • delete
        • get
        • list
      • projects.locations.evaluationRuns
        • Overview
        • cancel
        • create
        • delete
        • get
        • list
      • projects.locations.evaluationSets
        • Overview
        • create
        • delete
        • get
        • list
        • patch
      • projects.locations.models
        • Overview
        • getIamPolicy
        • setIamPolicy
        • testIamPermissions
      • projects.locations.operations
        • Overview
        • cancel
        • delete
        • get
        • list
        • wait
      • projects.locations.publishers.models
        • Overview
        • computeTokens
        • countTokens
        • embedContent
        • fetchPredictOperation
        • generateContent
        • predict
        • predictLongRunning
        • rawPredict
        • serverStreamingPredict
        • streamGenerateContent
        • streamRawPredict
      • projects.locations.ragCorpora
        • Overview
        • create
        • delete
        • get
        • list
        • patch
      • projects.locations.ragCorpora.ragFiles
        • Overview
        • delete
        • get
        • import
        • list
      • projects.locations.reasoningEngines
        • Overview
        • create
        • delete
        • get
        • list
        • patch
        • query
        • streamQuery
      • projects.locations.reasoningEngines.memories
        • Overview
        • create
        • delete
        • generate
        • get
        • list
        • patch
        • purge
        • retrieve
        • rollback
      • projects.locations.reasoningEngines.memories.revisions
        • Overview
        • get
        • list
      • projects.locations.reasoningEngines.sessions
        • Overview
        • appendEvent
        • create
        • delete
        • get
        • list
        • patch
      • projects.locations.reasoningEngines.sessions.events
        • Overview
        • list
      • projects.locations.tuningJobs
        • Overview
        • cancel
        • create
        • get
        • list
        • rebaseTunedModel
      • Types
      • AgentConfig
      • ApiAuth
      • ApiKeyConfig
      • BigQueryDestination
      • ComputeTokensResponse
      • Content
      • CountTokensResponse
      • EncryptionSpec
      • EnvVar
      • Fact
      • GcsDestination
      • GcsSource
      • GenerateContentResponse
      • GroundingMetadata
      • HarmBlockThreshold
      • HarmCategory
      • InstanceData
      • JobState
      • ManagedTopicEnum
      • MemoryTopicId
      • ModalityTokenCount
      • ModelArmorConfig
      • PredictResponse
      • RagChunk
      • RagEngineConfig
      • RagFileTransformationConfig
      • Rubric
      • SafetySetting
      • Schema
      • SessionEvent
      • StreamingPredictResponse
      • Tensor
    • v1beta1
      • REST Resources
      • media
        • Overview
        • upload
      • projects
        • Overview
        • getCacheConfig
        • updateCacheConfig
      • projects.locations
        • Overview
        • augmentPrompt
        • corroborateContent
        • evaluateDataset
        • evaluateInstances
        • generateInstanceRubrics
        • generateSyntheticData
        • getRagEngineConfig
        • retrieveContexts
        • updateRagEngineConfig
      • projects.locations.batchPredictionJobs
        • Overview
        • cancel
        • create
        • delete
        • get
        • list
      • projects.locations.cachedContents
        • Overview
        • create
        • delete
        • get
        • list
        • patch
      • projects.locations.endpoints
        • Overview
        • computeTokens
        • countTokens
        • fetchPredictOperation
        • generateContent
        • getIamPolicy
        • predict
        • predictLongRunning
        • rawPredict
        • serverStreamingPredict
        • setIamPolicy
        • streamGenerateContent
        • streamRawPredict
        • testIamPermissions
      • projects.locations.endpoints.chat
        • Overview
        • completions
      • projects.locations.endpoints.deployedModels.invoke
        • Overview
        • invoke
      • projects.locations.endpoints.google.science
        • Overview
        • inference
      • projects.locations.endpoints.invoke
        • Overview
        • invoke
      • projects.locations.endpoints.openapi
        • Overview
        • embeddings
      • projects.locations.evaluationItems
        • Overview
        • create
        • delete
        • get
        • list
      • projects.locations.evaluationRuns
        • Overview
        • cancel
        • create
        • delete
        • get
        • list
      • projects.locations.evaluationSets
        • Overview
        • create
        • delete
        • get
        • list
        • patch
      • projects.locations.extensions
        • Overview
        • delete
        • execute
        • get
        • import
        • list
        • patch
        • query
      • projects.locations.models
        • Overview
        • getIamPolicy
        • setIamPolicy
        • testIamPermissions
      • projects.locations.operations
        • Overview
        • cancel
        • delete
        • get
        • list
        • wait
      • projects.locations.publishers
        • Overview
        • getIamPolicy
      • projects.locations.publishers.models
        • Overview
        • computeTokens
        • countTokens
        • embedContent
        • fetchPredictOperation
        • generateContent
        • getIamPolicy
        • predict
        • predictLongRunning
        • rawPredict
        • serverStreamingPredict
        • streamGenerateContent
        • streamRawPredict
      • projects.locations.ragCorpora
        • Overview
        • create
        • delete
        • get
        • list
        • patch
      • projects.locations.ragCorpora.ragFiles
        • Overview
        • delete
        • get
        • import
        • list
      • projects.locations.reasoningEngines
        • Overview
        • create
        • delete
        • get
        • list
        • patch
        • query
        • streamQuery
      • projects.locations.reasoningEngines.a2a.v1
        • Overview
        • card
      • projects.locations.reasoningEngines.a2a.v1.message
        • Overview
        • send
        • stream
      • projects.locations.reasoningEngines.a2a.v1.tasks
        • Overview
        • a2aGetReasoningEngine
        • cancel
        • pushNotificationConfigs
        • subscribe
      • projects.locations.reasoningEngines.a2a.v1.tasks.pushNotificationConfigs
        • Overview
        • a2aGetReasoningEngine
      • projects.locations.reasoningEngines.memories
        • Overview
        • create
        • delete
        • generate
        • get
        • list
        • patch
        • purge
        • retrieve
        • rollback
      • projects.locations.reasoningEngines.memories.revisions
        • Overview
        • get
        • list
      • projects.locations.reasoningEngines.sessions
        • Overview
        • appendEvent
        • create
        • delete
        • get
        • list
        • patch
      • projects.locations.reasoningEngines.sessions.events
        • Overview
        • list
      • projects.locations.tuningJobs
        • Overview
        • cancel
        • create
        • get
        • list
        • optimizePrompt
        • rebaseTunedModel
      • Types
      • AgentConfig
      • AggregationMetric
      • ApiAuth
      • ApiKeyConfig
      • AuthConfig
      • AutoraterConfig
      • BigQueryDestination
      • BigQuerySource
      • CacheConfig
      • ComputeTokensResponse
      • Content
      • CountTokensResponse
      • EncryptionSpec
      • EnvVar
      • Fact
      • FunctionDeclaration
      • GcsDestination
      • GcsSource
      • GenerateContentResponse
      • GenerationConfig
      • GroundingMetadata
      • HarmBlockThreshold
      • HarmCategory
      • InstanceData
      • JobState
      • ManagedTopicEnum
      • MemoryTopicId
      • Metric
      • ModalityTokenCount
      • ModelArmorConfig
      • PredictResponse
      • RagChunk
      • RagEngineConfig
      • RagFileChunkingConfig
      • RagFileMetadataConfig
      • RagFileParsingConfig
      • RagFileTransformationConfig
      • Rubric
      • SafetySetting
      • Schema
      • SessionEvent
      • StreamingPredictResponse
      • Tensor
      • Tool
    • Shared types
      • Types
      • AlternateInitConfig
      • AuditConfig
      • BackgroundSwapProcessingConfig
      • Binding
      • BoundingPoly
      • CacheConfig
      • CancelOperationRequest
      • ControlNetConfig
      • ControlType
      • Date
      • DeleteOperationRequest
      • EditConfig
      • EditConfigV6
      • EditMode
      • GenSelfieConfig
      • GetIamPolicyRequest
      • GetOperationRequest
      • HttpBody
      • ImageOutputOptions
      • LatLng
      • ListOperationsRequest
      • ListOperationsResponse
      • LogType
      • MaskMode
      • NamedBoundingBox
      • OutpaintingProcessingConfig
      • OutputOptions
      • Policy
      • ReferenceType
      • SafetyAttributes
      • SemanticFilterConfig
      • SemanticFilterResponse
      • SetIamPolicyRequest
      • SubjectType
      • TaskType
      • TestIamPermissionsRequest
      • TestIamPermissionsResponse
      • TextEmbedding
      • TextEmbeddingPredictionInstance
      • TextEmbeddingPredictionParams
      • TextEmbeddingPredictionResult
      • UpscaleConfig
      • VideoGenerationModelInstance
      • VideoGenerationModelParams
      • VideoGenerationModelResult
      • VirtualTryOnModelInstance
      • VirtualTryOnModelParams
      • VirtualTryOnModelResultProto
      • VisionEmbeddingModelInstance
      • VisionEmbeddingModelParams
      • VisionEmbeddingModelResult
      • VisionGenerativeModelInstance
      • VisionGenerativeModelParams
      • VisionGenerativeModelResult
      • VisionReasoningModelInstance
      • VisionReasoningModelParams
      • VisionReasoningModelResult
      • WaitOperationRequest
  • RPC
    • Overview
    • cloud.ai.platform.common
    • google.api
    • google.cloud.aiplatform.v1
      • Overview
      • schema
        • Overview
        • predict.instance
        • predict.params
        • predict.prediction
    • google.cloud.aiplatform.v1beta1
      • Overview
      • schema
        • Overview
        • predict.instance
        • predict.params
        • predict.prediction
    • google.iam.v1
    • google.longrunning
    • google.rpc
    • google.type
  • Capabilities
    • Gemini API
      • Generate content
      • Function calling
      • Prompt classes
      • Grounding
      • Code execution API
      • Live API
      • API errors
    • Embeddings API
      • Text embeddings
      • Multimodal embeddings
    • Imagen API
      • Generate images
      • Edit images
      • Customize images (few-shot)
      • Virtual Try-On API
      • Product Recontext API
      • Upscale API
    • Veo video generation API
    • Lyria music generation API
    • Batch prediction API
    • Tuning API
    • Gen AI Evaluation API
    • RAG API
      • RAG API v1beta1
      • RAG API v1
      • Retrieval and generation output of RAG
    • CountTokens API
    • MedLM API
  • Google Gen AI SDK
  • Overview
  • Python
  • Go
  • Java
  • Node.js
  • Vertex AI SDK
  • Overview
  • Python
  • Node.js
  • Java
  • Go
  • C#
  • Agent Development Kit (ADK)
  • Overview
  • AI and ML