File size: 1,675 Bytes
447ebeb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
"""
This file is used to calculate the cost of the Gemini API.

Handles the context caching for Gemini API.
"""

from typing import TYPE_CHECKING, Tuple

if TYPE_CHECKING:
    from litellm.types.utils import ModelInfo, Usage


def cost_per_token(model: str, usage: "Usage") -> Tuple[float, float]:
    """
    Calculates the cost per token for a given model, prompt tokens, and completion tokens.

    Follows the same logic as Anthropic's cost per token calculation.
    """
    from litellm.litellm_core_utils.llm_cost_calc.utils import generic_cost_per_token

    return generic_cost_per_token(
        model=model, usage=usage, custom_llm_provider="gemini"
    )


def cost_per_web_search_request(usage: "Usage", model_info: "ModelInfo") -> float:
    """
    Calculates the cost per web search request for a given model, prompt tokens, and completion tokens.
    """
    from litellm.types.utils import PromptTokensDetailsWrapper

    # cost per web search request
    cost_per_web_search_request = 35e-3

    number_of_web_search_requests = 0
    # Get number of web search requests
    if (
        usage is not None
        and usage.prompt_tokens_details is not None
        and isinstance(usage.prompt_tokens_details, PromptTokensDetailsWrapper)
        and hasattr(usage.prompt_tokens_details, "web_search_requests")
        and usage.prompt_tokens_details.web_search_requests is not None
    ):
        number_of_web_search_requests = usage.prompt_tokens_details.web_search_requests
    else:
        number_of_web_search_requests = 0

    # Calculate total cost
    total_cost = cost_per_web_search_request * number_of_web_search_requests

    return total_cost