{"id":120983,"url":"https://github.com/viktorfa/awesome-serverless-gpu","name":"awesome-serverless-gpu","description":"Curated list of services and platforms for serverless GPU and AI inference","projects_count":60,"last_synced_at":"2026-06-09T02:00:35.130Z","repository":{"id":225320727,"uuid":"765656749","full_name":"viktorfa/awesome-serverless-gpu","owner":"viktorfa","description":"Curated list of services and platforms for serverless GPU and AI inference","archived":false,"fork":false,"pushed_at":"2025-03-26T13:59:27.000Z","size":32,"stargazers_count":49,"open_issues_count":2,"forks_count":2,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-05-23T11:02:46.997Z","etag":null,"topics":["ai","gpu","serverless"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/viktorfa.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-03-01T11:04:21.000Z","updated_at":"2026-05-14T15:41:25.000Z","dependencies_parsed_at":"2024-03-11T01:41:16.987Z","dependency_job_id":"36e04179-b42e-48bb-aa68-78243f612eb1","html_url":"https://github.com/viktorfa/awesome-serverless-gpu","commit_stats":null,"previous_names":["viktorfa/awesome-serverless-gpu"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/viktorfa/awesome-serverless-gpu","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/viktorfa%2Fawesome-serverless-gpu","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/viktorfa%2Fawesome-serverless-gpu/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/viktorfa%2Fawesome-serverless-gpu/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/viktorfa%2Fawesome-serverless-gpu/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/viktorfa","download_url":"https://codeload.github.com/viktorfa/awesome-serverless-gpu/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/viktorfa%2Fawesome-serverless-gpu/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34088013,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-09T02:00:06.510Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2026-02-22T19:39:19.245Z","updated_at":"2026-06-09T02:00:35.130Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Predefined models over API","Dev on GPUs","Inference","AI Agents for Websites","Workflow platforms"],"sub_categories":["Text to speech","Not serverless inference","Predefined models","Bring your own model","Speech to text","Image generation"],"readme":"# Awesome Serverless GPU\n\nList of where to run code on GPUs for AI, inference, predictions that are serverless.  \nServerless is defined as pay-as-you-go, scale-to-zero, minimal infrastructure configuration.\n\nServerless GPU is a reletively new and fast evolving field. New services are appearing and disappearing frequently.  \nI will do my best to keep the list updated, and soon include benchmarks.\n\nCommon weaknessses of serverless GPU at the moment is very long cold starts, and configuration that are less easy to use than the more mature field of serverless on CPUs.\n\n\n## Inference\n\n### Bring your own model\nTrue serverless inference\n- [Inferless.com](https://www.inferless.com/)\n- [Replicate.com](https://replicate.com/)\n- [Runpod.io](https://www.runpod.io/)\n- [Modelz.ai](https://modelz.ai/)\n- [Banana.dev](https://www.banana.dev/) (Shutting down March 31st 2024)\n- [Beam.cloud](https://www.beam.cloud/)\n- [Mystic.ai](https://www.mystic.ai/)\n- [Modal.com](https://modal.com/)\n- [Baseten.co](https://www.baseten.co/)\n- [Covalent.xyz](https://www.covalent.xyz/)\n\n### Predefined models\nTrue serverless with a limited set of models\n- [Cloudflare AI](https://ai.cloudflare.com/)\n- [OpenAI](https://platform.openai.com/)\n- [Mistral](https://docs.mistral.ai/)\n- [Sievedata.com](https://www.sievedata.com/)\n- [Together.ai](https://www.together.ai/)\n- [Anyscale.com](https://www.anyscale.com/)\n- [Fireworks.ai](https://fireworks.ai/)\n- [Fal.ai](https://fal.ai/)\n\n### Not serverless inference\nNeeds dedicated server, but works with your own model  \n- [Together.ai](https://www.together.ai/)\n- [Sievedata.com](https://www.sievedata.com/)\n- [Anyscale.com](https://www.anyscale.com/)\n- [Runpod.io](https://www.runpod.io/)\n- [Huggingface.co](https://huggingface.co/)\n- [Lepton.ai](https://www.lepton.ai/)\n- [Vast.ai](https://vast.ai/)\n- [Lambdalabs.com](https://lambdalabs.com/)\n- [Paperspace](https://www.paperspace.com/)\n\n\n## Dev on GPUs\nFlexible on-demand GPU providers\n- [Brev.dev](https://brev.dev/)\n- [Colab](https://colab.research.google.com/)\n- [Kaggle.com](https://www.kaggle.com/)\n- [Modal.com](https://modal.com/)\n- [Beam.cloud](https://www.beam.cloud/)\n\n\n## Predefined models over API\n\n### Speech to text\n- [OpenAI](https://platform.openai.com/docs/models/whisper)\n- [Amazon](https://aws.amazon.com/transcribe/), [Azure](https://azure.microsoft.com/en-us/products/ai-services/speech-to-text), [Google](https://cloud.google.com/speech-to-text)\n- [Gladia.io](https://www.gladia.io/)\n- [Deepgram.com](https://deepgram.com/)\n- [Speechmatics.com](https://www.speechmatics.com/)\n- [Sieve ASR](https://www.sievedata.com/functions/sieve/speech_transcriber)\n- [Fal.ai Whisper](https://fal.ai/models/fal-ai/whisper)\n- [Elevenlabs.io](https://elevenlabs.io/api)\n\n### Text to speech\n- [OpenAI](https://platform.openai.com/docs/guides/text-to-speech)\n- [Amazon](https://aws.amazon.com/polly/), [Azure](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech), [Google](https://cloud.google.com/text-to-speech)\n- [Speechify.com](https://speechify.com/)\n- [Elevenlabs.io](https://elevenlabs.io/api)\n- [Unrealspeech.com](https://unrealspeech.com/)\n- [Play.ht](https://play.ht/)\n- [Murf.ai](https://murf.ai/)\n- [Deepgram.com](https://deepgram.com/)\n- [Resemble.ai](https://www.resemble.ai/)\n\n### Image generation\n- [OpenAI Dall-e](https://platform.openai.com/docs/guides/images/introduction)\n- [Dreamstudio](https://dreamstudio.com/api/)\n- [Stablediffusionapi.com](https://stablediffusionapi.com/docs/)\n- [Modelslab.com](https://docs.modelslab.com/image-editing/overview)\n- [Bria.ai](https://bria.ai/)\n- [Fal.ai](https://fal.ai/models)\n\n## Workflow platforms\n- [Leap](https://www.tryleap.ai/)\n\n## AI Agents for Websites\n- [Chatflow](https://chatflow.no/)\n- [OneAI](https://oneai.com/)\n- [SiteGPT](https://sitegpt.ai/)\n- [Chatbase](https://www.chatbase.co/)\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/viktorfa%2Fawesome-serverless-gpu/projects"}