Skip to content

cloud

cloud

Cloud inference engine — OpenAI, Anthropic, and Google API backends.

Classes

CloudEngine 

CloudEngine()

Bases: InferenceEngine

Cloud inference via OpenAI, Anthropic, and Google SDKs.

Source code in src/openjarvis/engine/cloud.py 
136
137
138
139
140
def __init__(self) -> None:
    self._openai_client: Any = None
    self._anthropic_client: Any = None
    self._google_client: Any = None
    self._init_clients()

Functions

estimate_cost 

estimate_cost(model: str, prompt_tokens: int, completion_tokens: int) -> float

Estimate USD cost based on the hardcoded pricing table.

Source code in src/openjarvis/engine/cloud.py 
84
85
86
87
88
89
90
91
92
93
94
95
96
97
def estimate_cost(model: str, prompt_tokens: int, completion_tokens: int) -> float:
    """Estimate USD cost based on the hardcoded pricing table."""
    # Try exact match first, then prefix match
    prices = PRICING.get(model)
    if prices is None:
        for key, val in PRICING.items():
            if model.startswith(key):
                prices = val
                break
    if prices is None:
        return 0.0
    input_cost = (prompt_tokens / 1_000_000) * prices[0]
    output_cost = (completion_tokens / 1_000_000) * prices[1]
    return input_cost + output_cost