The cost math — when AI video is viable and when it bankrupts you (step 6/6) · ai video generation

Checkpoint

One last thing before we move on. pass this to mark the lesson done, or skip and keep moving.

Final footage drill. Synthesize price + retake + quality into a router: route_to_model(budget, quality_floor, retake_tolerance) that takes:

budget (float): max dollars per finished minute the user can spend.
quality_floor (str): minimum acceptable quality, one of "ai_flavored", "client_grade", "premium".
retake_tolerance (float): the retake multiplier the user expects to hit.

Each model has a quality_tier per this table:

Model	quality_tier	$/sec
Veo 3.1 Lite (720p+audio)	`ai_flavored`	0.05
Runway gen4_turbo I2V	`ai_flavored`	0.05
Omni 1.1 Flash (720p)	`client_grade`	0.10
Veo 3.1 Fast (720p+audio)	`client_grade`	0.10
Runway gen4.5	`client_grade`	0.12
Veo 3.1 Standard (audio)	`premium`	0.40

Quality ordering (each tier accepts higher tiers as substitutes): ai_flavored < client_grade < premium. So if quality_floor == "client_grade", both client_grade and premium models are eligible.

Algorithm:

Filter models down to those whose quality_tier is >= quality_floor.
Compute each eligible model's $/min real = price_per_sec × 60 × retake_tolerance.
Keep only models where $/min real <= budget.
From the remaining set, return the CHEAPEST one (lowest $/min real). On a tie, prefer the model that appears EARLIER in the PRICES dict order.
If no model fits, return "NO MATCH".

Five scenarios run. Expected output:

$3 + ai_flavored + 1.0x          -> Veo 3.1 Lite (720p+audio)
$8 + ai_flavored + 2.5x          -> Veo 3.1 Lite (720p+audio)
$6 + client_grade + 1.0x         -> Omni 1.1 Flash (720p)
$24 + premium + 1.0x             -> Veo 3.1 Standard (audio)
$2 + client_grade + 1.0x         -> NO MATCH