Struct ModelCapabilities 

pub struct ModelCapabilities {

    pub supports_tools: bool,
    pub supports_vision: bool,
    pub supports_audio: bool,
    pub supports_json_mode: bool,
    pub supports_streaming: bool,
    pub supports_system_prompt: bool,
    pub context_window: u32,
    pub max_output_tokens: u32,
    pub supports_reasoning: bool,
    pub supports_code_execution: bool,
    pub cost_tier: String,
    pub speed_tier: String,
    pub quality_tier: String,
    pub languages: HashSet<String>,
    pub family: Option<String>,
    pub production_ready: bool,
    pub is_local: bool,
    pub tags: HashSet<String>,
}

Capabilities that an LLM model may support.

These are used for intelligent model selection based on task requirements.

Fields

supports_tools: bool

Whether the model supports tool/function calling

supports_vision: bool

Whether the model supports vision/image inputs

supports_audio: bool

Whether the model supports audio inputs

supports_json_mode: bool

Whether the model supports structured output (JSON mode)

supports_streaming: bool

Whether the model supports streaming responses

supports_system_prompt: bool

Whether the model supports system prompts

context_window: u32

Maximum context window size in tokens

max_output_tokens: u32

Maximum output tokens the model can generate

supports_reasoning: bool

Whether the model has reasoning/chain-of-thought capabilities

supports_code_execution: bool

Whether the model supports code execution

cost_tier: String

Cost tier: “free”, “low”, “medium”, “high”, “premium”

speed_tier: String

Speed tier: “slow”, “medium”, “fast”, “realtime”

quality_tier: String

Quality tier: “basic”, “standard”, “high”, “premium”

languages: HashSet<String>

Supported languages (empty = all languages)

family: Option<String>

Model family (e.g., “gpt-4”, “claude-3”, “llama-3”)

production_ready: bool

Whether this model is suitable for production use

is_local: bool

Whether this model runs locally (no API calls)

tags: HashSet<String>

Custom capability tags for extension

Implementations

impl ModelCapabilities

pub fn for_model(model_name: &str) -> Self

Create capabilities for a known model by name.

This provides sensible defaults for popular models.

pub fn satisfies(&self, requirements: &CapabilityRequirements) -> bool

Check if this model satisfies the given requirements.

pub fn score(&self, requirements: &CapabilityRequirements) -> u32

Calculate a score for how well this model matches requirements.

Higher score = better match. Used for ranking when multiple models satisfy requirements.

Trait Implementations

impl Clone for ModelCapabilities

fn clone(&self) -> ModelCapabilities

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ModelCapabilities

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for ModelCapabilities

fn default() -> ModelCapabilities

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ModelCapabilities

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ModelCapabilities

fn eq(&self, other: &ModelCapabilities) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for ModelCapabilities

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ModelCapabilities