# How to Reduce Costs ### Test Before Final Generation **For videos:** 1. Start with **480p** resolution to test your prompt 2. Review the result and adjust if needed 3. Once satisfied, generate the final version in **720p** or **1080p** This approach can save 50-70% on testing costs. **For images:** 1. Set **batch size to 1** for initial testing 2. Refine your prompt until you’re happy with the result 3. Then generate multiple images in a batch ### Avoid Parameter Mismatch Some models have parameters that must be consistent: **Example: Seedream Sequential** If your prompt says “generate 4 images”, make sure `max_images` is set to 4. ``` Prompt: "Create 4 variations of a logo design..."max_images: 4 ✓ Correctmax_images: 2 ✗ Mismatch - may cause unexpected charges ``` ### Start with Ultra Fast Models Use the **Ultra Fast** series for testing and iteration: * Lower cost per generation * Faster results for quick validation * Great for prompt refinement ### Volume Discounts For high-volume users, contact for custom pricing options.
--- # 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://infronai.gitbook.io/docs/media-apis/best-practices/how-to-reduce-costs.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.