Class: Anthropic::Models::Beta::Sessions::BetaManagedAgentsSpanModelUsage

Inherits:
Internal::Type::BaseModel show all
Defined in:
lib/anthropic/models/beta/sessions/beta_managed_agents_span_model_usage.rb

Defined Under Namespace

Modules: Speed

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods inherited from Internal::Type::BaseModel

==, #==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, inspect, #inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml

Methods included from Internal::Type::Converter

#coerce, coerce, #dump, dump, #inspect, inspect, meta_info, new_coerce_state, type_info

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Constructor Details

#initialize(cache_creation_input_tokens:, cache_read_input_tokens:, input_tokens:, output_tokens:, speed: nil) ⇒ Object

Some parameter documentations has been truncated, see Anthropic::Models::Beta::Sessions::BetaManagedAgentsSpanModelUsage for more details.

Token usage for a single model request.

Parameters:

  • cache_creation_input_tokens (Integer) —

    Tokens used to create prompt cache in this request.

  • cache_read_input_tokens (Integer) —

    Tokens read from prompt cache in this request.

  • input_tokens (Integer) —

    Input tokens consumed by this request.

  • output_tokens (Integer) —

    Output tokens generated by this request.

  • speed (Symbol, Anthropic::Models::Beta::Sessions::BetaManagedAgentsSpanModelUsage::Speed, nil) (defaults to: nil) —

    Inference speed mode. ‘fast` provides significantly faster output token generati




# File 'lib/anthropic/models/beta/sessions/beta_managed_agents_span_model_usage.rb', line 42

Instance Attribute Details

#cache_creation_input_tokens ⇒ Integer

Tokens used to create prompt cache in this request.

Returns:

  • (Integer) 


12
 
# File 'lib/anthropic/models/beta/sessions/beta_managed_agents_span_model_usage.rb', line 12

required :cache_creation_input_tokens, Integer

#cache_read_input_tokens ⇒ Integer

Tokens read from prompt cache in this request.

Returns:

  • (Integer) 


18
 
# File 'lib/anthropic/models/beta/sessions/beta_managed_agents_span_model_usage.rb', line 18

required :cache_read_input_tokens, Integer

#input_tokens ⇒ Integer

Input tokens consumed by this request.

Returns:

  • (Integer) 


24
 
# File 'lib/anthropic/models/beta/sessions/beta_managed_agents_span_model_usage.rb', line 24

required :input_tokens, Integer

#output_tokens ⇒ Integer

Output tokens generated by this request.

Returns:

  • (Integer) 


30
 
# File 'lib/anthropic/models/beta/sessions/beta_managed_agents_span_model_usage.rb', line 30

required :output_tokens, Integer

#speed ⇒ Symbol, ...

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.

Returns:



38
39
40
 
# File 'lib/anthropic/models/beta/sessions/beta_managed_agents_span_model_usage.rb', line 38

optional :speed,
enum: -> { Anthropic::Beta::Sessions::BetaManagedAgentsSpanModelUsage::Speed },
nil?: true