Skip to content

savings

savings

Savings calculation — compare local inference cost against cloud providers.

Classes

ProviderSavings dataclass 

ProviderSavings(provider: str = '', label: str = '', input_cost: float = 0.0, output_cost: float = 0.0, total_cost: float = 0.0, energy_wh: float = 0.0, energy_joules: float = 0.0, flops: float = 0.0)

Savings compared to a single cloud provider.

SavingsSummary dataclass 

SavingsSummary(total_calls: int = 0, total_prompt_tokens: int = 0, total_completion_tokens: int = 0, total_tokens: int = 0, local_cost: float = 0.0, per_provider: List[ProviderSavings] = list(), monthly_projection: Dict[str, float] = dict(), session_start_ts: float = 0.0, session_duration_hours: float = 0.0, avg_cost_per_query: Dict[str, float] = dict(), cloud_agent_equivalent: Dict[str, int] = dict())

Overall savings summary across all cloud providers.

Functions

compute_savings 

compute_savings(prompt_tokens: int, completion_tokens: int, total_calls: int = 0, session_start: float = 0.0) -> SavingsSummary

Compute savings vs cloud providers given token counts.

Source code in src/openjarvis/server/savings.py 
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
def compute_savings(
    prompt_tokens: int,
    completion_tokens: int,
    total_calls: int = 0,
    session_start: float = 0.0,
) -> SavingsSummary:
    """Compute savings vs cloud providers given token counts."""
    total_tokens = prompt_tokens + completion_tokens
    providers: List[ProviderSavings] = []

    now = time.time()
    session_duration_hours = (now - session_start) / 3600 if session_start > 0 else 0.0

    monthly_projection: Dict[str, float] = {}
    avg_cost_per_query: Dict[str, float] = {}

    for key, pricing in CLOUD_PRICING.items():
        input_cost = (prompt_tokens / 1_000_000) * pricing["input_per_1m"]
        output_cost = (completion_tokens / 1_000_000) * pricing["output_per_1m"]
        total_cost = input_cost + output_cost
        energy_wh = (total_tokens / 1000) * pricing["energy_wh_per_1k_tokens"]
        flops = total_tokens * pricing["flops_per_token"]

        providers.append(ProviderSavings(
            provider=key,
            label=pricing["label"],
            input_cost=input_cost,
            output_cost=output_cost,
            total_cost=total_cost,
            energy_wh=energy_wh,
            energy_joules=energy_wh * 3600,  # 1 Wh = 3600 J
            flops=flops,
        ))

        # Monthly projection: extrapolate current spend to 720 hours/month
        if session_duration_hours > 0:
            monthly_projection[key] = (total_cost / session_duration_hours) * 720
        else:
            monthly_projection[key] = 0.0

        # Average cost per query
        if total_calls > 0:
            avg_cost_per_query[key] = total_cost / total_calls
        else:
            avg_cost_per_query[key] = 0.0

    return SavingsSummary(
        total_calls=total_calls,
        total_prompt_tokens=prompt_tokens,
        total_completion_tokens=completion_tokens,
        total_tokens=total_tokens,
        local_cost=0.0,
        per_provider=providers,
        monthly_projection=monthly_projection,
        session_start_ts=session_start,
        session_duration_hours=session_duration_hours,
        avg_cost_per_query=avg_cost_per_query,
        cloud_agent_equivalent={
            "moderate_low": 15,
            "moderate_high": 60,
            "heavy_low": 100,
            "heavy_high": 400,
        },
    )

savings_to_dict 

savings_to_dict(summary: SavingsSummary) -> Dict[str, Any]

Convert SavingsSummary to a JSON-serializable dict.

Source code in src/openjarvis/server/savings.py 
138
139
140
def savings_to_dict(summary: SavingsSummary) -> Dict[str, Any]:
    """Convert SavingsSummary to a JSON-serializable dict."""
    return asdict(summary)