Inferless
Inferless provides a serverless GPU inference platform designed for deploying machine learning models quickly and affordably.
Our verdict
Who it's for
Deploy and scale machine learning models on serverless GPUs in minutes.
Who should look elsewhere
Specific pricing details for enterprise plans require direct contact
Pros
- +Eliminates infrastructure management for GPU clusters
- +Scales automatically with workload, paying only for usage
- +Achieves sub-second cold starts for large models
- +Provides significant cost savings compared to traditional GPU clusters
- +Offers enterprise-grade security with SOC-2 Type II certification
Cons
- −Specific pricing details for enterprise plans require direct contact
- −Currently in private beta for certain offerings, requiring waitlist access
Key features
- ✓One-click deployment from Hugging Face, Git, Docker, or CLI
- ✓Automatic scaling from zero to hundreds of GPUs
- ✓Customizable container runtimes
- ✓NFS-like writable volumes with simultaneous connections
- ✓Automated CI/CD for model re-imports
- ✓Detailed call and build logs for monitoring
- ✓Dynamic batching for increased throughput
- ✓Customizable private endpoints (scale down, timeout, concurrency, testing, webhooks)
Pricing
| Plan | Price | Billing | Notes |
|---|---|---|---|
| Starter | $0.000555 | month | Designed for small teams and independent developers; Deploy models in minutes without worrying about the cost |
| Enterprise | — | month | Built for fast-growing startups and larger organizations; Scale quickly at an affordable cost with desired latency results |
| Nvidia T4 Dedicated | $0.000185 | month | GPU RAM: 16GB; vCPUs: 3x; RAM: 20GB |
| Nvidia A10 Dedicated | $0.000341 | month | GPU RAM: 24GB; vCPUs: 7x; RAM: 30GB |
| Nvidia A100 Dedicated | $0.001491 | month | GPU RAM: 80GB; vCPUs: 20x; RAM: 200GB |
| Nvidia T4 Shared | $0.000092 | month | GPU RAM: 8GB; vCPUs: 1.5x; RAM: 10GB |
| Nvidia A10 Shared | $0.00017 | month | GPU RAM: 12GB; vCPUs: 3x; RAM: 15GB |
| Nvidia A100 Shared | $0.000745 | month | GPU RAM: 40GB; vCPUs: 10x; RAM: 100GB |
| Volume Pricing - Storage | $50 | month | 50 GB free every month; Extra storage costs $0.3/GB/month |
| Join Waitlist (Startup) | — | month | Min 10,000 Inference Requests per month; Unlimited deployed webhook endpoints; GPU concurrency of 5 |
| Get Early Access (Enterprise) | — | month | Min 100,000 Inference Requests per month; Unlimited deployed webhook endpoints; GPU concurrency of 50 |