Claude Platform Docs

Dreams

Create a Dream
beta.dreams.create(DreamCreateParams**kwargs) -> BetaDream
POST/v1/dreams
List Dreams
beta.dreams.list(DreamListParams**kwargs) -> SyncPageCursor[BetaDream]
GET/v1/dreams
Get a Dream
beta.dreams.retrieve(strdream_id, DreamRetrieveParams**kwargs) -> BetaDream
GET/v1/dreams/{dream_id}
Cancel a Dream
beta.dreams.cancel(strdream_id, DreamCancelParams**kwargs) -> BetaDream
POST/v1/dreams/{dream_id}/cancel
Archive a Dream
beta.dreams.archive(strdream_id, DreamArchiveParams**kwargs) -> BetaDream
POST/v1/dreams/{dream_id}/archive
Models
class BetaDream:

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.

class BetaDreamError:

Failure detail for a Dream whose status is failed.

message: str
type: str

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:
class BetaDreamMemoryStoreInput:

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: str
minLength1
type: Literal["memory_store"]
class BetaDreamSessionsInput:

Input session transcripts the dream reads.

session_ids: List[str]
type: Literal["sessions"]
class BetaDreamMemoryStoreInput:

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: str
minLength1
type: Literal["memory_store"]
class BetaDreamMemoryStoreOutput:

An output memory store the dream writes consolidated memories into.

memory_store_id: str
type: Literal["memory_store"]
class BetaDreamModelConfig:

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

id: str

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

minLength1
maxLength256
speed: Optional[Literal["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"
class BetaDreamModelConfigParam:

Model identifier and configuration applied to every pipeline stage.

id: str

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

minLength1
maxLength256
speed: Optional[Literal["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"
class BetaDreamOutput:

An output memory store the dream writes consolidated memories into.

memory_store_id: str
type: Literal["memory_store"]
class BetaDreamSessionsInput:

Input session transcripts the dream reads.

session_ids: List[str]
type: Literal["sessions"]
Literal["pending", "running", "completed", 2 more]

Lifecycle status of a Dream.

One of the following:
"pending"
"running"
"completed"
"failed"
"canceled"
class BetaDreamUsage:

Cumulative token usage for the dream across every pipeline stage.

cache_creation_input_tokens: int

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

formatint32
cache_read_input_tokens: int

Total tokens read from prompt cache.

formatint32
input_tokens: int

Total uncached input tokens consumed across every pipeline stage.

formatint32
output_tokens: int

Total output tokens generated across every pipeline stage.

formatint32

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:
class BetaOutputBehaviorCreateNew:

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: Literal["create_new"]
class BetaOutputBehaviorUpdateExisting:

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: str
minLength1
type: Literal["update_existing"]
class BetaOutputBehaviorCreateNew:

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: Literal["create_new"]
class BetaOutputBehaviorUpdateExisting:

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: str
minLength1
type: Literal["update_existing"]