- Home
- Model Hosting
- Runpod Serverless
On the recordRead 9 Oct 202616 facts
Runpod Serverless
San Francisco, California, United States
Plans and prices
Serverless GPU endpoint (141GB H200)
Free
H200 · 141 GB
Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (16GB class)
Free
A4000, A4500, RTX 4000, RTX 2000 · 16 GB
Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (24GB class)
Free
L4, A5000, 3090, MIG 24GB · 24 GB
Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (32GB 5090)
Free
5090 · 32 GB
Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (32GB RTX PRO 4500 Blackwell)
Free
RTX PRO 4500 Blackwell · 32 GB
Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (48GB A6000/A40)
Free
A6000, A40 · 48 GB
Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (48GB L40/L40S/6000 Ada/MIG)
Free
L40, L40S, 6000 Ada, MIG 48GB · 48 GB
Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (80GB A100)
Free
A100 · 80 GB
Read 9 Oct 2026 · runpod.io
Serverless GPU endpoint (80GB H100)
Free
H100 · 80 GB
Read 9 Oct 2026 · runpod.io
On the record
- Autoscaling
- The product overview says endpoints scale from zero to hundreds of workers with request demand, and flex workers scale to zero when idle.runpod.io · read 9 Oct 2026
- Billing
- Serverless compute is billed per second from worker start to full stop, rounded up to the nearest second.runpod.io · read 9 Oct 2026
- Cold starts
- FlashBoot is described as providing sub-200ms cold starts, while pre-warmed workers can provide zero cold starts.runpod.io · read 9 Oct 2026
- 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.runpod.io · read 9 Oct 2026
- 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.runpod.io · read 9 Oct 2026
- Deployments
- Workers can be deployed from GitHub, with code and Dockerfile built into a container image and deployed to an endpoint.docs.runpod.io · read 9 Oct 2026
- Integrations
- The documentation describes OpenAI-compatible endpoint integration with tools including n8n, CrewAI, and LangChain.docs.runpod.io · read 9 Oct 2026
- Intended workloads
- The product page identifies inference, fine-tuning, agent systems, rendering, and simulations as workloads for Serverless.runpod.io · read 9 Oct 2026
- Purpose
- Runpod Serverless runs containerized AI inference workloads behind API endpoints and scales workers based on demand.runpod.io · read 9 Oct 2026
- Regions
- The product page says users can deploy in global regions to place workloads closer to users.runpod.io · read 9 Oct 2026
- SDKs
- Runpod documents Serverless SDKs for Python, JavaScript, and Go.docs.runpod.io · read 9 Oct 2026
- 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.runpod.io · read 9 Oct 2026
- Storage
- The product page describes persistent network storage that scales with workloads.runpod.io · read 9 Oct 2026
- Support
- Runpod documentation directs users to submit a support request, check the service status page, or join its Discord community.docs.runpod.io · read 9 Oct 2026