Batch AI Image Generation

A production-oriented Python starter for bulk AI image generation with concurrency control, retries, resumable JSONL results, and a preflight cost ceiling.

It is a practical AI image generation API client for large prompt lists rather than a single-image demo.

Use it for ecommerce catalogs, ad-creative batches, dataset generation, thumbnails, product mockups, and other high-volume image API workloads.

Install

python -m pip install -r requirements.txt
copy .env.example .env.local

Set APIMART_API_KEY in your environment, then run:

python batch_generate.py prompts.example.jsonl --model gpt-image-2-ext --workers 4 --estimated-cost-per-image 0.0085 --max-cost 1.00

Input is JSON Lines:

{"id":"catalog-001","prompt":"Studio product photo of a ceramic bottle on limestone","size":"1024x1024"}

The script writes one result per prompt to results.jsonl. Existing successful IDs are skipped on the next run.

Why APIMart is relevant

APIMart is a unified AI API gateway with hundreds of text, image, video, and audio models. High-volume teams can use one account for keys, usage, billing, and current pricing instead of maintaining separate provider integrations.

• Compare current image-model prices
• Read the image API quickstart

Model availability and prices change. The cost ceiling is an estimate, not a billing guarantee.

Related high-volume AI API tools

• AI API Load Tester — test latency, throughput, and 429 handling
• LLM API Cost Calculator — forecast text, image, and video spend
• AI Generation Benchmarks — inspect prompts, raw outputs, latency, and reported cost

Test

python -m unittest discover -s tests

Project directory

This repository is part of the APIMART open-source AI API toolkit. Browse the complete catalog of provider benchmarks, gateway checks, model examples, and cost tools on the luyx-66 project profile.

License

MIT