Skip to content

13 offerings · 13 billing options

Products: Serverless

13 of 13 offerings verified recently

11 identified GPU models

View official pricing source →

How the service works

Hand-reviewed product behavior. Exact current prices and billing units remain in the tables below.

Serverless

Hand-reviewed 2026-07-18 · review after 2026-10-18

Setup: moderate

Deployment
A provider-specific handler runs inside a custom container behind a managed queue endpoint. Images can be supplied from a container registry or deployed from a GitHub repository.
queued worker · synchronous http · asynchronous job · task queue
Scale to zero
Flex workers scale dynamically to zero when idle. Active workers are a separate always-running option for workloads that must avoid cold starts.
supported · default
Billing behavior
Flex workers are billed from worker startup until complete shutdown, including initialization and the configured idle timeout, rounded to the provider's billing increment. Storage is charged separately.
Startup behavior
Cold-start time depends on image download, worker initialization and model loading. Cached models and FlashBoot can reduce it, but the general worker path has no single guaranteed end-to-end cold-start time.
Setup
The standard workflow requires a Runpod handler, local container testing, an image registry or GitHub deployment, and endpoint/GPU configuration in the Runpod console or API.
Requires: Runpod account · Runpod handler integration · Docker image or GitHub repository · Serverless endpoint configuration
Important constraints
  • Several lower-cost GPU classes group multiple GPU models, so exact hardware and performance may vary within the selected class.
  • Worker concurrency limits depend on account balance unless increased by support.

Serverless GPU prices

1× RTX 4090 · 24 GB VRAM/GPU
4090 · Serverless · fixed
  • USD 1.1/hour
    gpu time
≈ EUR 0.962/hour
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.
1× NVIDIA GeForce RTX 5090 · 32 GB VRAM/GPU
5090 · Serverless · fixed
  • USD 1.58/hour
    gpu time
≈ EUR 1.382/hour
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.
1× A100 · 80 GB VRAM/GPU
A100 · Serverless · fixed
  • USD 2.72/hour
    gpu time
≈ EUR 2.379/hour
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.
No guaranteed GPU model · VRAM unknown
A4000, A4500, RTX 4000, RTX 2000 · Serverless · opaque provider tier
  • USD 0.58/hour
    gpu time
Component price — not a total
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.
1× A6000 / A40 · 48 GB VRAM/GPU
A6000, A40 · Serverless · provider selected pool
  • USD 1.22/hour
    gpu time
Component price — not a total
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.
1× NVIDIA B200 · 180 GB VRAM/GPU
B200 · Serverless · fixed
  • USD 8.64/hour
    gpu time
≈ EUR 7.556/hour
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.
1× NVIDIA B300 · 280 GB VRAM/GPU
B300 · Serverless · fixed
  • USD 9.98/hour
    gpu time
≈ EUR 8.728/hour
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.
1× H100 · 80 GB VRAM/GPU
H100 · Serverless · fixed
  • USD 4.55/hour
    gpu time
≈ EUR 3.979/hour
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.
1× NVIDIA H200 · 140 GB VRAM/GPU
H200 · Serverless · fixed
  • USD 5.93/hour
    gpu time
≈ EUR 5.186/hour
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.
No guaranteed GPU model · 24 GB VRAM/GPU
L4, A5000, 3090, MIG 24GB · Serverless · opaque provider tier
  • USD 0.69/hour
    gpu time
Component price — not a total
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.
No guaranteed GPU model · 48 GB VRAM/GPU
L40, L40S, 6000 Ada, MIG 48GB · Serverless · opaque provider tier
  • USD 1.75/hour
    gpu time
Component price — not a total
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.
1× NVIDIA RTX PRO 6000 Blackwell · 96 GB VRAM/GPU
RTX 6000 Pro · Serverless · fixed
  • USD 3.49/hour
    gpu time
≈ EUR 3.052/hour
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.
1× NVIDIA RTX PRO 4500 Blackwell · 32 GB VRAM/GPU
RTX PRO 4500 Blackwell · Serverless · fixed
  • USD 1.15/hour
    gpu time
≈ EUR 1.006/hour
Flex
scale to zero
1 second increments · bills initialization, execution, idle timeout
Active worker discounts are available through sales inquiry and are omitted because no public price is published.

Other GPU Providers