> For the complete documentation index, see [llms.txt](https://docs.qolaba.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.qolaba.ai/video-generation/understanding-credit-usage.md). # Understanding Credit Usage Every video generation in Qolaba consumes credits. The total cost of a generation is not fixed — it varies based on the model you select, the quality and duration you configure, whether audio is included, and how many outputs you produce in a single run. Understanding how these factors interact helps you generate efficiently and avoid unnecessary credit consumption. *** #### What Affects Credit Cost Credit cost per video is determined by four factors. Each one independently influences the per-video cost — and they compound when combined: 1. **Model** Each model has a different base credit cost per generation. Premium models with higher realism, longer duration support, or advanced capabilities cost more per video than faster, lighter models. 2. **Resolution** Higher resolution increases the per-video cost: * 720p — lowest cost * 1080p — standard cost * 4K — highest cost 3. **Duration** Longer videos consume more credits: * Shorter durations (1–4 seconds) — lower cost * Longer durations (6–8 seconds) — higher cost 4. **Audio** Applicable to Seedance and Seedance 2.5 only. Generating video with audio costs slightly more than generating silent video. *** #### How Total Credits Are Calculated All per-video factors combine into a single per-video cost, which is then multiplied by the number of generations you have configured: > **Total credits = credits per video × number of generations** The **credits per video** reflects your combined choice of model, resolution, duration, and audio setting. The number of generations then multiplies that figure to produce the total cost for the run. **Example:** | Setting | Value | | --------------------- | --------- | | Model | Veo 3.1 | | Resolution | 1080p | | Duration | 8 seconds | | Audio | Off | | Credits per video | 800 | | Number of generations | 3 | | **Total credits** | **2,400** | Change any one setting — reduce duration to 4 seconds, drop resolution to 720p, or reduce generations to 1 — and the total cost decreases accordingly. *** #### Reviewing Cost Before You Generate Before committing to a generation, the total credit cost for your current configuration is displayed on the **Generate button**. Review this before clicking — if the cost is higher than expected, adjust your settings and the cost updates immediately to reflect the change. This is particularly important when: * Running a batch of multiple generations * Generating at 4K for the first time with a new prompt * Switching to a higher-cost model mid-workflow {% hint style="info" %} Get into the habit of checking the cost on the Generate button before every run — especially when changing model, resolution, or generation count. {% endhint %} *** #### Optimizing Credit Usage 1. **Test at Low Cost First** The most effective way to manage credit usage is to validate your prompt, model, and reference inputs before generating at high quality or in batch. 2. **Recommended draft configuration:** * Duration: **4 seconds** * Resolution: **720p** * Generations: **1** * Audio: **Off** This produces a meaningful output at the lowest possible cost. Motion quality, prompt adherence, composition, and visual style are all evaluable at this setting — there is no need to generate at 1080p or 4K until the direction is confirmed. *** **Draft vs. Final Generation Strategy** Treat every generation workflow as two stages: * **Stage 1 — Draft** Run at 720p, 4 seconds, single generation. Evaluate the output. Refine your prompt, keywords, or reference media if needed. Repeat until the direction is confirmed. * **Stage 2 — Final** Once satisfied with the draft output, upgrade to your target resolution and duration and generate the final version. If multiple variations are needed for client comparison or selection, increase the generation count at this stage only. This two-stage approach consistently produces better outputs at lower total credit cost than attempting to generate final-quality outputs from the start. *** **Additional Credit-Saving Practices** * **Use A/B generation strategically** — Setting generations to 2 on a confirmed prompt is more credit-efficient than running two separate single generations * **Match resolution to delivery format** — Don't generate at 4K for content that will be delivered at 1080p or lower * **Use shorter durations for concept validation** — A 4-second draft is sufficient to evaluate motion, composition, and style before committing to an 8-second final * **Disable audio during drafts** — If using Seedance, turn audio off during testing and enable it only for final generations * **Choose cost-efficient models for iteration** — Use faster, lighter models like Veo 3.1 Fast or Kling 3 for prompt testing, and reserve premium models for final outputs *** #### Credit Usage by Configuration The table below shows how different configurations affect relative credit cost — from lowest to highest: | Configuration | Relative Cost | | -------------------------- | ------------- | | 720p + 4s + 1 generation | Lowest | | 720p + 8s + 1 generation | Low | | 1080p + 4s + 1 generation | Low–Moderate | | 1080p + 8s + 1 generation | Moderate | | 1080p + 8s + 2 generations | Moderate–High | | 4K + 8s + 1 generation | High | | 4K + 8s + 3 generations | Highest | {% hint style="info" %} Exact credit costs vary by model. The table above reflects relative cost relationships across settings — not absolute credit values. See [Video Models →](/model-reference/video-models.md) for per-model credit cost indicators. {% endhint %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.qolaba.ai/video-generation/understanding-credit-usage.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.