Claude Platform Docs

Dreams

Create a Dream
client.beta.dreams.create(DreamCreateParamsparams, RequestOptionsoptions?): BetaDream
POST/v1/dreams
List Dreams
client.beta.dreams.list(DreamListParamsparams?, RequestOptionsoptions?): PageCursor<BetaDream>
GET/v1/dreams
Get a Dream
client.beta.dreams.retrieve(stringdreamID, DreamRetrieveParamsparams?, RequestOptionsoptions?): BetaDream
GET/v1/dreams/{dream_id}
Cancel a Dream
client.beta.dreams.cancel(stringdreamID, DreamCancelParamsparams?, RequestOptionsoptions?): BetaDream
POST/v1/dreams/{dream_id}/cancel
Archive a Dream
client.beta.dreams.archive(stringdreamID, DreamArchiveParamsparams?, RequestOptionsoptions?): BetaDream
POST/v1/dreams/{dream_id}/archive
Models
BetaDream { id, archived_at, created_at, 11 more }

An asynchronous memory-consolidation job that reads a memory store plus a set of session transcripts and writes consolidated memories into an output memory store — a new store by default, or an existing store chosen via output_behavior. The Dreams API is in research preview: the request and response shapes are volatile and may change without the deprecation period that applies to generally-available endpoints.

BetaDreamError { message, type }

Failure detail for a Dream whose status is failed.

message: string
type: string
BetaDreamInput = BetaDreamMemoryStoreInput { memory_store_id, type } | BetaDreamSessionsInput { session_ids, type }

An input memory store the dream reads from. The dream never mutates this store unless it is also the destination: with output_behavior {type: "update_existing"} the job consolidates this store in place.

One of the following:
BetaDreamMemoryStoreInput { memory_store_id, type }

An input memory store the dream reads from. The dream never mutates this store unless it is also the destination: with output_behavior {type: "update_existing"} the job consolidates this store in place.

memory_store_id: string
minLength1
type: "memory_store"
BetaDreamSessionsInput { session_ids, type }

Input session transcripts the dream reads.

session_ids: Array<string>
type: "sessions"
BetaDreamMemoryStoreInput { memory_store_id, type }

An input memory store the dream reads from. The dream never mutates this store unless it is also the destination: with output_behavior {type: "update_existing"} the job consolidates this store in place.

memory_store_id: string
minLength1
type: "memory_store"
BetaDreamMemoryStoreOutput { memory_store_id, type }

An output memory store the dream writes consolidated memories into.

memory_store_id: string
type: "memory_store"
BetaDreamModelConfig { id, speed }

Model identifier and configuration applied to every pipeline stage. Same wire shape as the Agents API ModelConfig.

id: string

Model identifier, e.g. "claude-opus-5". 1-256 characters.

minLength1
maxLength256
speed?: "standard" | "fast"

Inference speed mode. fast provides significantly faster output token generation at premium pricing. Not all models support fast; invalid combinations are rejected at create time.

One of the following:
"standard"
"fast"
BetaDreamModelConfigParam { id, speed }

Model identifier and configuration applied to every pipeline stage.

id: string

Model identifier, e.g. "claude-opus-5". 1-256 characters.

minLength1
maxLength256
speed?: "standard" | "fast" | null

Inference speed mode. fast provides significantly faster output token generation at premium pricing. Not all models support fast; invalid combinations are rejected at create time.

One of the following:
"standard"
"fast"
BetaDreamOutput { memory_store_id, type }

An output memory store the dream writes consolidated memories into.

memory_store_id: string
type: "memory_store"
BetaDreamSessionsInput { session_ids, type }

Input session transcripts the dream reads.

session_ids: Array<string>
type: "sessions"
BetaDreamStatus = "pending" | "running" | "completed" | 2 more

Lifecycle status of a Dream.

One of the following:
"pending"
"running"
"completed"
"failed"
"canceled"
BetaDreamUsage { cache_creation_input_tokens, cache_read_input_tokens, input_tokens, output_tokens }

Cumulative token usage for the dream across every pipeline stage.

cache_creation_input_tokens: number

Total tokens used to create prompt-cache entries (sum of all TTL tiers).

formatint32
cache_read_input_tokens: number

Total tokens read from prompt cache.

formatint32
input_tokens: number

Total uncached input tokens consumed across every pipeline stage.

formatint32
output_tokens: number

Total output tokens generated across every pipeline stage.

formatint32
BetaOutputBehavior = BetaOutputBehaviorCreateNew { type } | BetaOutputBehaviorUpdateExisting { memory_store_id, type }

The default destination: the job creates a new output memory store as a clone of the memory_store input and writes the consolidated memories into it. The input store is never mutated.

One of the following:
BetaOutputBehaviorCreateNew { type }

The default destination: the job creates a new output memory store as a clone of the memory_store input and writes the consolidated memories into it. The input store is never mutated.

type: "create_new"
BetaOutputBehaviorUpdateExisting { memory_store_id, type }

The job writes the consolidated memories into this existing memory store instead of creating one. In EAP the store must be the job's own memory_store input, so the job consolidates the store in place.

memory_store_id: string
minLength1
type: "update_existing"
BetaOutputBehaviorCreateNew { type }

The default destination: the job creates a new output memory store as a clone of the memory_store input and writes the consolidated memories into it. The input store is never mutated.

type: "create_new"
BetaOutputBehaviorUpdateExisting { memory_store_id, type }

The job writes the consolidated memories into this existing memory store instead of creating one. In EAP the store must be the job's own memory_store input, so the job consolidates the store in place.

memory_store_id: string
minLength1
type: "update_existing"