Skip to content
SPECIFICTION
Get listed

Runpod Serverless

runpod.io

Free plan WebWindowsmacOSLinuxAPI
Visit runpod.io
Spec score 7.7 #5 of 25 in Model Hosting

Spec sheet

Purpose
Runpod Serverless runs containerized AI inference workloads behind API endpoints and scales workers based on demand.Read 9 Oct 2026 · runpod.io
Integrations
The documentation describes OpenAI-compatible endpoint integration with tools including n8n, CrewAI, and LangChain.Read 9 Oct 2026 · docs.runpod.io
Support
Runpod documentation directs users to submit a support request, check the service status page, or join its Discord community.Read 9 Oct 2026 · docs.runpod.io
Headquarters
San Francisco, California, United StatesRead 28 Sep 2026 · runpod.io
Founded
2022Read 28 Sep 2026 · runpod.io
Autoscaling
The product overview says endpoints scale from zero to hundreds of workers with request demand, and flex workers scale to zero when idle.Read 9 Oct 2026 · runpod.io
Billing
Serverless compute is billed per second from worker start to full stop, rounded up to the nearest second.Read 9 Oct 2026 · runpod.io
Cold starts
FlashBoot is described as providing sub-200ms cold starts, while pre-warmed workers can provide zero cold starts.Read 9 Oct 2026 · runpod.io
Compliance scope
Runpod says compliance coverage can vary by workload, region, provider, and deployment model, and directs customers to confirm specific requirements with its team.Read 9 Oct 2026 · runpod.io
Containers and runtimes
Users can bring a Docker container and configure runtimes for languages and frameworks including Python, Node.js, Go, Rust, C++, PyTorch, TensorFlow, JAX, and ONNX.Read 9 Oct 2026 · runpod.io
Deployments
Workers can be deployed from GitHub, with code and Dockerfile built into a container image and deployed to an endpoint.Read 9 Oct 2026 · docs.runpod.io
Intended workloads
The product page identifies inference, fine-tuning, agent systems, rendering, and simulations as workloads for Serverless.Read 9 Oct 2026 · runpod.io
Regions
The product page says users can deploy in global regions to place workloads closer to users.Read 9 Oct 2026 · runpod.io
SDKs
Runpod documents Serverless SDKs for Python, JavaScript, and Go.Read 9 Oct 2026 · docs.runpod.io
Security and compliance
Runpod states that it completed SOC 2 Type II and SOC 3 examinations, maintains HIPAA and GDPR programs, and holds an ISO/IEC 27001:2022 certification for its information security management system.Read 9 Oct 2026 · runpod.io
Storage
The product page describes persistent network storage that scales with workloads.Read 9 Oct 2026 · runpod.io

Plans and prices

Serverless GPU endpoint (141GB H200) Free $5.93/hr, metered per second H200 · 141 GB Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (16GB class) Free $0.58/hr, metered per second A4000, A4500, RTX 4000, RTX 2000 · 16 GB Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (24GB class) Free $0.69/hr, metered per second L4, A5000, 3090, MIG 24GB · 24 GB Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (32GB 5090) Free $1.58/hr, metered per second 5090 · 32 GB Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (32GB RTX PRO 4500 Blackwell) Free $1.15/hr, metered per second RTX PRO 4500 Blackwell · 32 GB Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (48GB A6000/A40) Free $1.22/hr, metered per second A6000, A40 · 48 GB Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (48GB L40/L40S/6000 Ada/MIG) Free $1.75/hr, metered per second L40, L40S, 6000 Ada, MIG 48GB · 48 GB Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (80GB A100) Free $2.72/hr, metered per second A100 · 80 GB Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (80GB H100) Free $4.79/hr, metered per second H100 · 80 GB Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (96GB RTX 6000 Pro) Free $3.49/hr, metered per second RTX 6000 Pro · 96 GB Read 9 Oct 2026 · runpod.io

Every Runpod Serverless plan and price →

Where Specifiction places it

Alternatives to Runpod ServerlessAll alternatives →