AI Video Generation API Cost Comparison
Enter kept clips per month, seconds per clip, takes per kept clip and a resolution once. The calculator prices every Runway Dev video model offered at that resolution — Gen-4.5, Gen-4 Turbo, Aleph 2.0, Veo 3.1 / Fast, Kling 3.0 / 4.0, Seedance 2.0 / 2.5, WAN 3.0, MiniMax H3 and Gemini Omni Flash 1.1 — applies minimum durations and charges, and sorts them by cost per finished clip, with audio-included flags and Gemini API direct for Omni Flash at 720p. Estimates only; official pricing pages prevail.
Math runs in your browser. Nothing is uploaded.
Cheapest per finished clip
—
Gemini API direct
—
| # | Model (Runway Dev) | $/s | Audio | Minimum | Per generation | Per finished clip | Monthly |
|---|
Formula: per finished clip = max(seconds, minimum) × $/s (floored at any minimum charge, rounded up to $0.01) × takes; monthly = clips × per finished clip. Only models offered at the chosen resolution are listed (Gen-4.5, Gen-4 Turbo, Aleph 2.0 and Act Two bill one rate at any resolution; MiniMax 768p is shown under 720p). Audio: "Included" = always generated, "Yes/No" = with/without-audio rate, "—" = silent or not stated. All rates are Runway Dev list prices; Veo 3.1 direct on the Gemini API is not on Google's official Gemini API pricing page as of 2026-11-01, so it is not included.
Estimates only. Official list prices as of 2026-11-01 (Asia/Shanghai); the provider's pricing page prevails. Sources: Runway Dev pricing · Gemini API pricing
Gemini Omni Flash Video Cost Calculator · Runway API Cost Calculator · Gemini Image Cost Calculator · OpenAI Image API Cost Calculator · AI Image Generation API Cost Comparison · fal.ai Cost Calculator
More in this group
- Gemini Omni Flash Video Cost Calculator Omni Flash 1.1: Gemini API vs Runway $/clip & $/mo.
- Runway API Cost Calculator Runway Dev model $/s → per clip, per month, recipes.
- Gemini Image Cost Calculator Nano Banana images by resolution and Batch.
- OpenAI Image API Cost Calculator GPT Image tokens with optional Batch half-price.
- AI Image Generation API Cost Comparison 20+ image models ranked by $ per kept image.
How it works
- Which AI video generation API is cheapest?
- It depends on resolution and audio. At 720p on Runway Dev the lowest per-second rates are Gen-4 Turbo and Act Two at $0.05/s, MiniMax H3 Max (768p) $0.08/s, Kling 3.0 Standard $0.09/s, then WAN 3.0, Veo 3.1 Fast (no audio) and Omni Flash 1.1 at $0.10/s — but minimums and audio change the ranking.
- Why compare cost per finished clip, not per second?
- Most usable clips take several generations. Cost per finished clip = per-generation cost × takes, so a cheaper model you must re-roll three times can cost more than a pricier model that lands on the first try.
- Which models include audio?
- Gemini Omni Flash 1.1 always includes audio. Veo 3.1 and Kling 3.0 have separate with-audio and without-audio rates (Veo 3.1 $0.40 vs $0.20/s). Other models are marked '—' where audio is not part of the listed rate.
- Why isn't Veo 3.1 via the Gemini API listed?
- At ship time (2026-11-01) Google's official Gemini API pricing page listed Gemini Omni Flash for video generation but not Veo 3.1, so we use Runway Dev's Veo 3.1 rates only and do not quote unofficial third-party numbers.
- How do minimum durations affect short clips?
- A 2-second clip on Seedance 2.0 bills 4 seconds, on MiniMax H3 Max 5 seconds, and Aleph 2.0 never costs less than $0.56 per generation. The table applies each model's minimum before ranking.