ModelPreferences implements JsonSerializable
The server's preferences for model selection, requested of the client during sampling.
Because LLMs can vary along multiple dimensions, choosing the "best" model is rarely straightforward. Different models excel in different areas—some are faster but less capable, others are more capable but more expensive, and so on. This interface allows servers to express their priorities across multiple dimensions to help clients make an appropriate selection for their use case.
These preferences are always advisory. The client MAY ignore them. It is also up to the client to decide how to interpret these preferences and how to balance them against other considerations.
Tags
Table of Contents
Interfaces
- JsonSerializable
Properties
- $costPriority : float|null
- $hints : array<string|int, mixed>|null
- $intelligencePriority : float|null
- $speedPriority : float|null
Methods
- __construct() : mixed
- fromArray() : self
- jsonSerialize() : ModelPreferencesData
Properties
$costPriority read-only
public
float|null
$costPriority
= null
$hints read-only
public
array<string|int, mixed>|null
$hints
= null
$intelligencePriority read-only
public
float|null
$intelligencePriority
= null
$speedPriority read-only
public
float|null
$speedPriority
= null
Methods
__construct()
public
__construct([array<string|int, ModelHint>|null $hints = null ][, float|null $costPriority = null ][, float|null $speedPriority = null ][, float|null $intelligencePriority = null ]) : mixed
Parameters
- $hints : array<string|int, ModelHint>|null = null
-
Optional hints about the model to use.
If multiple hints are specified, the client MUST evaluate them in order (such that the first match is taken).
The client SHOULD prioritize these hints over the numeric priorities, but MAY still use the priorities to select from ambiguous matches.
- $costPriority : float|null = null
-
How much to prioritize cost when selecting a model. A value of 0 means cost is not important, while a value of 1 means cost is the most important factor. Minimum value is 0, maximum value is 1.
- $speedPriority : float|null = null
-
How much to prioritize sampling speed (latency) when selecting a model. A value of 0 means speed is not important, while a value of 1 means speed is the most important factor. Minimum value is 0, maximum value is 1.
- $intelligencePriority : float|null = null
-
How much to prioritize intelligence and capabilities when selecting a model. A value of 0 means intelligence is not important, while a value of 1 means intelligence is the most important factor.
fromArray()
public
static fromArray(ModelPreferencesData $preferences) : self
Parameters
- $preferences : ModelPreferencesData
Return values
selfjsonSerialize()
public
jsonSerialize() : ModelPreferencesData