Claude Platform Docs

Models

List Models
models.list(ModelListParams**kwargs) -> SyncPage[ModelInfo]
GET/v1/models
Get a Model
models.retrieve(strmodel_id, ModelRetrieveParams**kwargs) -> ModelInfo
GET/v1/models/{model_id}
Models
class CapabilitySupport:

Indicates whether a capability is supported.

supported: bool

Whether this capability is supported by the model.

class ContextManagementCapability:

Context management capability details.

clear_thinking_20251015: Optional[CapabilitySupport]

Indicates whether a capability is supported.

supported: bool

Whether this capability is supported by the model.

clear_tool_uses_20250919: Optional[CapabilitySupport]

Indicates whether a capability is supported.

supported: bool

Whether this capability is supported by the model.

compact_20260112: Optional[CapabilitySupport]

Indicates whether a capability is supported.

supported: bool

Whether this capability is supported by the model.

supported: bool

Whether this capability is supported by the model.

class EffortCapability:

Effort (reasoning_effort) capability details.

Whether the model supports high effort level.

supported: bool

Whether this capability is supported by the model.

Whether the model supports low effort level.

supported: bool

Whether this capability is supported by the model.

Whether the model supports max effort level.

supported: bool

Whether this capability is supported by the model.

Whether the model supports medium effort level.

supported: bool

Whether this capability is supported by the model.

supported: bool

Whether this capability is supported by the model.

xhigh: Optional[CapabilitySupport]

Indicates whether a capability is supported.

supported: bool

Whether this capability is supported by the model.

class ModelCapabilities:

Model capability information.

class ModelInfo:
id: str

Unique model identifier.

capabilities: Optional[ModelCapabilities]

Model capability information.

created_at: datetime

RFC 3339 datetime string representing the time at which the model was released. May be set to an epoch value if the release date is unknown.

formatdate-time
display_name: str

A human-readable name for the model.

max_input_tokens: Optional[int]

Maximum input context window size in tokens for this model.

max_tokens: Optional[int]

Maximum value for the max_tokens parameter when using this model.

type: Literal["model"]

Object type.

For Models, this is always "model".

defaultmodel
class ThinkingCapability:

Thinking capability details.

supported: bool

Whether this capability is supported by the model.

Supported thinking type configurations.

Whether the model supports thinking with type 'adaptive' (auto).

supported: bool

Whether this capability is supported by the model.

Whether the model supports thinking with type 'enabled'.

supported: bool

Whether this capability is supported by the model.

class ThinkingTypes:

Supported thinking type configurations.

Whether the model supports thinking with type 'adaptive' (auto).

supported: bool

Whether this capability is supported by the model.

Whether the model supports thinking with type 'enabled'.

supported: bool

Whether this capability is supported by the model.