62 lines
3.4 KiB
Python
62 lines
3.4 KiB
Python
# EXAMPLE ONLY: an extract from the Superbill Review prototype, kept as reference for porting. ECW/eClinicalWorks, Tebra, 'Example Client', SPB_* tables and patient/ticket wording are that project's examples. Don't copy them into a new project.
|
|
INCLUDE_THINKING_IN_COST = True # thinking tokens bill at output rate
|
|
|
|
# ═════════════════════════════════════════════════════════════════════════════
|
|
# GEMINI PRICING TABLE
|
|
# ═════════════════════════════════════════════════════════════════════════════
|
|
PRICING_SOURCE = "https://ai.google.dev/gemini-api/docs/pricing"
|
|
PRICING_AS_OF = "2026-08-11"
|
|
|
|
GEMINI_PRICING = {
|
|
# ---- Gemini 3.x family --------------------------------------------------
|
|
"gemini-3.6-flash": {"input": 1.50, "output": 7.50, "free_tier": True},
|
|
"gemini-3.5-flash": {"input": 1.50, "output": 9.00, "free_tier": True},
|
|
"gemini-3.5-flash-lite": {"input": 0.30, "output": 2.50, "free_tier": True},
|
|
"gemini-3-flash-preview": {"input": 0.50, "output": 3.00, "free_tier": True},
|
|
"gemini-3.1-flash-lite": {"input": 0.25, "output": 1.50, "free_tier": True},
|
|
"gemini-3.1-pro-preview": {
|
|
"input": 2.00, "output": 12.00, "free_tier": False,
|
|
"long_threshold": 200_000, "input_long": 4.00, "output_long": 18.00,
|
|
},
|
|
# ---- Gemini 2.5 family --------------------------------------------------
|
|
"gemini-2.5-pro": {
|
|
"input": 1.25, "output": 10.00, "free_tier": True,
|
|
"long_threshold": 200_000, "input_long": 2.50, "output_long": 15.00,
|
|
},
|
|
"gemini-2.5-flash": {"input": 0.30, "output": 2.50, "free_tier": True},
|
|
"gemini-2.5-flash-lite": {"input": 0.10, "output": 0.40, "free_tier": True},
|
|
"gemini-2.5-flash-lite-preview-09-2025": {"input": 0.10, "output": 0.40, "free_tier": True},
|
|
# ---- Gemini 2.0 family (DEPRECATED — shut down 2026-06-01) --------------
|
|
"gemini-2.0-flash": {"input": 0.10, "output": 0.40, "free_tier": True, "deprecated": True},
|
|
"gemini-2.0-flash-lite": {"input": 0.075, "output": 0.30, "free_tier": True, "deprecated": True},
|
|
}
|
|
|
|
|
|
def resolve_pricing(model: str, input_tokens: int):
|
|
if model not in GEMINI_PRICING:
|
|
raise KeyError(
|
|
f"No pricing entry for model '{model}'. Add it to GEMINI_PRICING "
|
|
f"from {PRICING_SOURCE}. Known models: {', '.join(GEMINI_PRICING)}"
|
|
)
|
|
p = GEMINI_PRICING[model]
|
|
note = ""
|
|
in_rate, out_rate = p["input"], p["output"]
|
|
threshold = p.get("long_threshold")
|
|
if threshold and input_tokens > threshold:
|
|
in_rate = p.get("input_long", in_rate)
|
|
out_rate = p.get("output_long", out_rate)
|
|
note = f"long-context rate (>{threshold:,} input tokens)"
|
|
return in_rate, out_rate, note
|
|
|
|
|
|
def cost_for_call(model: str, usage: dict):
|
|
in_rate, out_rate, note = resolve_pricing(model, usage["input"])
|
|
billable_output = usage["output"]
|
|
if INCLUDE_THINKING_IN_COST:
|
|
billable_output += usage.get("thinking", 0)
|
|
input_cost = usage["input"] / 1_000_000 * in_rate
|
|
output_cost = billable_output / 1_000_000 * out_rate
|
|
return input_cost + output_cost, input_cost, output_cost, note
|
|
|
|
|