RunPod

Free tier

The AI Developer Cloud — experiment, train, fine-tune, deploy, and scale on one platform

Free tier available·Technical·API available

Key strengths

Sub-200ms cold starts via FlashBootAutoscaling from 0 to thousands of workersZero idle cost on Serverless31 global regions30+ GPU SKUs including H100, A100, B200, B300SOC 2 Type II certified, HIPAA and GDPR compliantPer-second billing with no contracts or minimum commitments

Free tier + paid plans · from $0.27 USD/mo

San Francisco, United States

Facts verified against runpod.io on Oct 23, 2026

Get alerts when RunPod changes

Free. We'll email you when pricing, the free tier, API access or open-source status changes.

No ratings yet

Runpod is a usage-based GPU cloud platform built for AI developers. It offers both Pods (persistent GPU instances) and Serverless (event-driven, autoscaling workers) compute modes. Pods are billed per-second or per-hour, ranging from $0.27/hr (RTX A5000) to $8.99/hr (B300). Serverless workers scale from 0 to thousands of instances with sub-200ms cold starts via FlashBoot, zero idle cost, and pricing from $8.64/hr (B200) to $10.65/hr (B300). The platform spans 31 global regions, offers 30+ GPU SKUs including H100, A100, B200, and B300, and exposes a full API for programmatic control. Integrations include Claude Code and Cursor. Runpod is SOC 2 Type II certified and compliant with HIPAA and GDPR. No contracts or minimum commitments are required; enterprise agreements are available.

Alternatives

Alternatives to RunPod

See all alternatives

Replicate

Free

AI infrastructure

Run open-source AI models in the cloud via a simple API — images, video, audio, and LLMs.

Pay-per-use: public models billed by time (e.g. CPU $0.000100/sec, Nvidia T4 $0.000225/sec, Nvidia L40S $0.000975/sec, Nvidia A100 80GB $0.001400/sec) or by input/output (e.g. flux-1.1-pro $0.04/image, deepseek-r1 $0.01/1K output tokens). Private models billed for all online time including idle.

Node.jsPythonHTTP

Free tierDevAPIOSS

Multi-provider (Black Forest Labs, OpenAI, Google, Anthropic, ByteDance, xAI, Alibaba, Recraft, Minimax, and community models)Popular

Modal

Free

AI infrastructure

High-performance AI infrastructure with sub-second cold starts and instant autoscaling

Starter plan is $0 + compute/month (includes $30/month free credits, 3 seats, 100 containers, 10 GPU concurrency). Team plan is $250 + compute/month (includes $100/month free credits, unlimited seats, 5000 containers, 50 GPU concurrency). Enterprise is custom pricing. Compute billed per second: e.g. H100 SXM5 at $0.001097/sec, CPU at $0.0000131/core/sec, Memory at $0.00000222/GiB/sec.

DatadogOpenTelemetryAWS MarketplaceGCP Marketplace+1

Free tierDevAPI

Popular

Cerebrium

Free

AI infrastructure

Serverless GPU infrastructure for real-time AI with sub-second cold starts and instant autoscaling

Pay-per-second compute pricing. Hobby plan is free (+ compute costs). Standard plan is $100/month + compute. Enterprise is custom. GPU rates range from $0.000164/s (T4) to $0.00167/s (B200). Memory at $0.00000222/GB/s, storage at $0.05/GB/mo (first 100GB free).

TwilioPipecatLiveKitvLLM+7

PaidDevAPI

Growing

NVIDIA DGX Cloud Lepton

AI infrastructure

Connect developers to a global network of GPU compute for building and deploying AI

Enterprise pricing; contact NVIDIA for details

NVIDIA Run:aiHuggingFaceCUDA-XNVIDIA AI Enterprise+1

PaidDevAPI

NVIDIA10M+ users

Together AI

Free

AI infrastructure

The AI Native Cloud — full-stack platform for inference, compute, and model shaping

Usage-based pricing for serverless inference (per token), batch inference, provisioned throughput (token-based capacity with SLAs), dedicated model inference, and dedicated container inference. GPU compute clusters also available.

GPU ClustersModel LibraryInference APIsFine-tuning+1

Free tierDevAPI

Open-source models (e.g., DeepSeek, Gemma, Llama, Qwen, GLM, MiniMax, Kimi)Popular

E2B

Free

AI infrastructure

The agent cloud — Every agent gets a machine

Free Hobby tier with $100 one-time usage credit (up to 1 hr sessions, 20 concurrent sandboxes). Pro at $150/month + usage billed by the second (up to 24 hr sessions, 100 concurrent sandboxes). Enterprise at custom pricing with committed usage, multi-day sessions, tens of thousands of concurrent sandboxes, and BYOC deployment.

OpenAI Agents SDKClaude CodeCodexCursor+9

Free tierEveryoneAPIOSSSelf-host

15k

Compare head-to-head:RunPod vs Replicate RunPod vs Modal RunPod vs Cerebrium

Browse all 35 ai infrastructure tools