{"data":{"slug":"ebhy-budgetml","name":"budgetml","tagline":"Deploy ML inference service on a budget","github_url":"https://github.com/ebhy/budgetml","owner":"ebhy","repo":"budgetml","owner_avatar_url":"https://avatars.githubusercontent.com/u/76654256?v=4","primary_language":"Python","stars":1344,"forks":65,"topics":["api","data-science","deployment","fastapi","inference","machine-learning","mlops"],"archived":false,"github_pushed_at":"2024-02-12T17:29:24+00:00","maintenance_label":"Dormant","stars_delta_30d":1,"url":"https://www.graphcanon.com/tools/ebhy-budgetml","markdown_url":"https://www.graphcanon.com/tools/ebhy-budgetml.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ebhy-budgetml","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ebhy-budgetml","description":"Deploy a ML inference service on a budget in less than 10 lines of code.","homepage_url":null,"license":"Apache-2.0","open_issues":4,"watchers":23,"ai_summary":"BudgetML is a Python library that enables users to deploy machine learning inference services using Google Cloud Preemptible instances to significantly reduce costs.","readme_excerpt":"## Cost comparison\nBudgetML uses Google Cloud Preemptible instances under-the-hood to reduce costs by 80%. This can potentially mean hundreds of dollars \nworth of savings. Here is a screenshot of the `e2-highmem` GCP series, which is regular family of instances to be using for \nmemory intense tasks like ML model inference functions. See the following price comparison (as of Jan 31, 2021 [[source](https://cloud.google.com/compute/vm-instance-pricing)])\n\n\n\nEven with the lowest machine_type, there is a **$46/month** savings, and with the highest configuration this is **$370/month** savings!\n\n---\n\n## Installation\nBudgetML is available for easy installation into your environment via PyPI:\n```bash\npip install budgetml\n```\nAlternatively, if you’re feeling brave, feel free to install the bleeding edge:\n\n**NOTE:** Do so at your own risk; no guarantees given!\n```bash\npip install git+https://github.com/ebhy/budgetml.git@main --upgrade\n```","github_created_at":"2020-12-27T14:24:57+00:00","created_at":"2026-07-11T23:16:11.005589+00:00","updated_at":"2026-09-20T04:30:34.165182+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"api","name":"api"},{"slug":"data-science","name":"data-science"},{"slug":"deployment","name":"deployment"},{"slug":"fastapi","name":"fastapi"},{"slug":"inference","name":"inference"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"mlops","name":"mlops"}],"trust":{"provenance":{"is_fork":false,"github_id":324778385,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:24:26.952Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":948,"last_release_at":"2021-01-31T20:26:15Z","stars_delta_30d":1,"open_issues_delta_30d":0},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:24:29.108Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:24:25.854Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:24:25.854Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-18T08:24:25.854Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"BudgetML is free to use under the Apache-2.0 license, but users must cover the cost of Google Cloud Preemptible instances, which can be up to 80 percent cheaper than regular instances."},"requirements":{"notes":["Requires access to Google Cloud Preemptible instances."],"min_ram_gb":4,"requires_docker":false},"constraints":{"min_ram_gb":4,"pricing_model":"freemium","requires_docker":false},"when_to_use":["When you need to deploy machine learning inference services with a tight budget, as BudgetML can reduce costs by up to 80 percent using Google Cloud Preemptible instances.","If your project involves memory-intensive tasks like ML model inference functions and you are looking for cost-effective solutions, BudgetML can save you up to $370 per month with the highest instance","When you want to deploy a service in less than 10 lines of code, making it ideal for quick prototyping or small-scale deployments."],"when_not_to_use":["If your application cannot tolerate the risk of instance preemption, as BudgetML relies on Google Cloud Preemptible instances that can be terminated with short notice.","When you require high availability and reliability, as preemptible instances can be interrupted, which might not be suitable for mission-critical applications.","If you are working in an environment where the use of external cloud services is restricted, BudgetML's reliance on Google Cloud might not be feasible."],"source":"enrich:decision_facts","observed_at":"2026-09-18T11:30:55.619Z"},"constraint_facets":{"min_ram_gb":4,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - BudgetML is free to use under the Apache-2.0 license, but users must cover the cost of Google Cloud Preemptible instances, which can be up to 80 percent cheaper than regular instances."},{"label":"Requirements","value":"Min 4 GB RAM; Requires access to Google Cloud Preemptible instances."},{"label":"Adopt for","value":"BudgetML is a Python library that facilitates the deployment of machine learning inference services using Google Cloud Preemptible instances, offering significant cost reductions."}]}}