Modal pricing: GPU rental rates
Updated October 2026 · updated 2026-10-06
The lowest published Modal rate is $0.590/GPU-hour for the Tesla T4 (serverless; No reservation; Not reported, updated 2026-10-06). Serverless compute, per-second GPU billing, $30/mo free credit. We track 11 live GPU offers across 11 models.
Compare the full daily GPU market
GPU prices compared with the market
| GPU | Provider lowest firm rate | Market median | Difference |
|---|
The market median gives each provider equal weight. GPU variants, node size, included CPU and memory can differ. A lower rate does not establish equivalent performance.
Live Modal prices (2026-10-06)
Provider, memory & availability
| GPU / provider | Billing | $/GPU-hour | GPUs / total per hour | Availability / details |
|---|---|---|---|---|
| Tesla T4Modal16 GB VRAM | serverless | $0.590per GPU-hour$0.000164/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L4Modal24 GB VRAM | serverless | $0.799per GPU-hour$0.000222/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| A10Modal24 GB VRAM | serverless | $1.10per GPU-hour$0.000306/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L40SModal48 GB VRAM | serverless | $1.95per GPU-hour$0.000542/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| A100 PCIe 40GBModal40 GB VRAM | serverless | $2.10per GPU-hour$0.000583/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| A100 (unspecified)Modal80 GB VRAM | serverless | $2.50per GPU-hour$0.000694/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| RTX PRO 6000 (unspecified)Modal96 GB VRAM | serverless | $3.03per GPU-hour$0.000842/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMModal80 GB VRAM | serverless | $3.95per GPU-hour$0.001097/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H200 (SXM)Modal141 GB VRAM | serverless | $4.54per GPU-hour$0.001261/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| B200Modal180 GB VRAM | serverless | $6.25per GPU-hour$0.001736/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| B300Modal288 GB VRAM | serverless | $7.10per GPU-hour$0.001972/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
Try another provider or reduce the minimum memory.
Tables rank by price, lowest first. Commercial relationships never affect ordering. How we collect and rank prices.
Monthly view assumes 730 hours of continuous use. Daily view assumes 24 hours.
Cheapest listed per-GPU-hour rates verified at the source. Before storage, egress and networking.
Modal access and company facts
| Check | Published information | Updated |
|---|---|---|
| Smallest recorded configuration | GPU count not reported for collected rates | 2026-10-06 |
| Published regions in this comparison | No per-configuration region recorded | 2026-10-06 |
| Minimum account funding | not published | 2026-07-07 |
| Data location terms | multi-region | 2026-07-07 |
A company fact or certification is not a guarantee for every product or region. Unrecorded fields are left unknown. The smallest recorded node does not establish immediate stock or account approval.
Strengths and trade-offs
Strengths
Trade-offs
- Egress pricing not published
- No published SLA
Computed from the verified fees and platform matrix (cells updated 2026-07-07 at Modal's own documentation; verified items link to their source). Full matrices: fees · enterprise.
Similar providers
Cerebrium
Serverless GPU platform, per-second billing; CPU/memory billed separately on top of the GPU rate.
from $0.590/hr serverless
9 GPU families in common
RunPod
Secure Cloud (datacenter, reliable) and Community Cloud (peer hosts, cheaper). Per-second billing, serverless option.
from $0.25/hr secure cloud
8 GPU families in common
Ranked by overlap in the GPU models both providers list today; not an endorsement and never affected by commercial relationships.
FAQ
The lowest published Modal rate is $0.590/GPU-hour for the Tesla T4 (serverless; No reservation; availability: Not reported; updated 2026-10-06). Configuration and billing conditions appear in each row.
Modal prices 11 GPU models, including H100, H200, A100, B200, B300. The live table above lists every current rate.
Modal prices are tracked as serverless. Every row is labeled with its tier and updated at the source on 2026-10-06.
Prices collected from modal.com, updated 2026-10-06. See the methodology for how each number is collected.