Struct InferenceCreateMessagesResponseUsage 

pub struct InferenceCreateMessagesResponseUsage {
    pub cache_creation_input_tokens: Option<i64>,
    pub cache_read_input_tokens: Option<i64>,
    pub input_tokens: i64,
    pub output_tokens: i64,
    pub speed: Option<InferenceCreateMessagesResponseUsageSpeed>,
}

Token usage for a non-streaming POST /v1/messages response.

JSON schema

{
 "description": "Token usage for a non-streaming `POST /v1/messages` response.",
 "type": "object",
 "required": [
   "input_tokens",
   "output_tokens"
 ],
 "properties": {
   "cache_creation_input_tokens": {
     "description": "Input tokens used to create a prompt cache entry, if applicable.",
     "examples": [
       0
     ],
     "type": "integer"
   },
   "cache_read_input_tokens": {
     "description": "Input tokens read from a prompt cache, if applicable.",
     "examples": [
       0
     ],
     "type": "integer"
   },
   "input_tokens": {
     "description": "Number of input tokens billed for this request.",
     "examples": [
       42
     ],
     "type": "integer"
   },
   "output_tokens": {
     "description": "Number of output tokens generated.",
     "examples": [
       128
     ],
     "type": "integer"
   },
   "speed": {
     "description": "Inference speed tier reflected in billing or routing.",
     "examples": [
       "standard"
     ],
     "type": [
       "string",
       "null"
     ],
     "enum": [
       "standard",
       "fast"
     ]
   }
 }
}

Fields

cache_creation_input_tokens: Option<i64>

Input tokens used to create a prompt cache entry, if applicable.

cache_read_input_tokens: Option<i64>

Input tokens read from a prompt cache, if applicable.

input_tokens: i64

Number of input tokens billed for this request.

output_tokens: i64

Number of output tokens generated.

speed: Option<InferenceCreateMessagesResponseUsageSpeed>

Inference speed tier reflected in billing or routing.

Trait Implementations

impl Clone for InferenceCreateMessagesResponseUsage

fn clone(&self) -> InferenceCreateMessagesResponseUsage

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for InferenceCreateMessagesResponseUsage

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for InferenceCreateMessagesResponseUsage

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl From<&InferenceCreateMessagesResponseUsage> for InferenceCreateMessagesResponseUsage

fn from(value: &InferenceCreateMessagesResponseUsage) -> Self

Converts to this type from the input type.

impl Serialize for InferenceCreateMessagesResponseUsage

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

where __S: Serializer,

Serialize this value into the given Serde serializer.