62 lines
2.2 KiB
Python
62 lines
2.2 KiB
Python
"""
|
|
Cost Tracker - Token cost estimation for API calls.
|
|
|
|
This module provides cost estimation for different LLM providers based on per-token pricing.
|
|
It is used to display estimated costs in the MMA Dashboard.
|
|
|
|
Pricing Data (per 1M tokens):
|
|
- gemini-2.5-flash-lite: $0.075 input / $0.30 output
|
|
- gemini-3-flash-preview: $0.15 input / $0.60 output
|
|
- gemini-3.1-pro-preview: $3.50 input / $10.50 output
|
|
- claude-*-sonnet: $3.0 input / $15.0 output
|
|
- claude-*-opus: $15.0 input / $75.0 output
|
|
- deepseek-v3: $0.27 input / $1.10 output
|
|
|
|
Usage:
|
|
from src.cost_tracker import estimate_cost
|
|
|
|
total = estimate_cost("gemini-2.5-flash-lite", 50000, 10000)
|
|
# Returns: 0.007 (approx)
|
|
|
|
Accuracy:
|
|
- Pricing data may be outdated
|
|
- Uses regex matching for model identification
|
|
- Returns 0.0 for unknown models
|
|
|
|
Integration:
|
|
- Used by gui_2.py for MMA dashboard cost display
|
|
- Called after each API call
|
|
|
|
See Also:
|
|
- src/ai_client.py for token tracking
|
|
- docs/guide_mma.md for MMA dashboard documentation
|
|
"""
|
|
import re
|
|
|
|
# Pricing per 1M tokens in USD
|
|
MODEL_PRICING = [
|
|
(r"gemini-2\.5-flash-lite", {"input_per_mtok": 0.075, "output_per_mtok": 0.30}),
|
|
(r"gemini-2\.5-flash", {"input_per_mtok": 0.15, "output_per_mtok": 0.60}),
|
|
(r"gemini-3-flash-preview", {"input_per_mtok": 0.15, "output_per_mtok": 0.60}),
|
|
(r"gemini-3\.1-pro-preview", {"input_per_mtok": 3.50, "output_per_mtok": 10.50}),
|
|
(r"claude-.*-sonnet", {"input_per_mtok": 3.0, "output_per_mtok": 15.0}),
|
|
(r"claude-.*-opus", {"input_per_mtok": 15.0, "output_per_mtok": 75.0}),
|
|
(r"deepseek-v3", {"input_per_mtok": 0.27, "output_per_mtok": 1.10}),
|
|
]
|
|
|
|
def estimate_cost(model: str, input_tokens: int, output_tokens: int) -> float:
|
|
"""
|
|
Estimate the cost of a model call based on input and output tokens.
|
|
Returns the total cost in USD.
|
|
"""
|
|
if not model:
|
|
return 0.0
|
|
|
|
for pattern, rates in MODEL_PRICING:
|
|
if re.search(pattern, model, re.IGNORECASE):
|
|
input_cost = (input_tokens / 1_000_000) * rates["input_per_mtok"]
|
|
output_cost = (output_tokens / 1_000_000) * rates["output_per_mtok"]
|
|
return input_cost + output_cost
|
|
|
|
return 0.0
|