Modal
- Categories
- Serverless containers, GPU clouds, Inference hosts
- Owned by
- Modal Labs (private)
- HQ
- US
- Website
- https://modal.com
- Pricing page
- https://modal.com/pricing
- Offers
- serverless containers, GPU, jobs
- Fee model
- per_second_gpu+subscription
- Fees
- Serverless GPU per second: B300 $0.001972/s, B200 $0.001736/s, H200 $0.001261/s, H100 $0.001097/s, RTX PRO 6000 $0.000842/s, A100 80GB $0.000694/s, A100 40GB $0.000583/s, L40S $0.000542/s, A10 $0.000306/s, L4 $0.000222/s, T4 $0.000164/s; CPU $0.0000131/core/s; memory $0.00000222/GiB/s. Plans: Starter $0 (+$30/mo free compute), Team $250/mo (+$100/mo free compute), Enterprise custom.
- Free tier
- $30/month free compute on Starter
- OpenAI-compatible API
- partial
- Notes
- You deploy your own model server (e.g. vLLM) — no public per-token price list, although Modal appears as a per-token upstream on OpenRouter for a few models.
- Sources
- https://modal.com/pricing collected 2026-09-18
GPU rates
| Provider | GPU | GPUs | VRAM/GPU | Billing | Per GPU-hr | Instance /hr | Region | Source |
|---|---|---|---|---|---|---|---|---|
| Modal | T4 | 1 | 16 GB | serverless per sec | $0.59 | $0.59 | ✓ src ⓘ | |
| Modal | L4 | 1 | 24 GB | serverless per sec | $0.799 | $0.799 | ✓ src ⓘ | |
| Modal | A10 | 1 | 24 GB | serverless per sec | $1.10 | $1.10 | ✓ src ⓘ | |
| Modal | L40S | 1 | 48 GB | serverless per sec | $1.95 | $1.95 | ✓ src ⓘ | |
| Modal | A100 40GB | 1 | 40 GB | serverless per sec | $2.10 | $2.10 | ✓ src ⓘ | |
| Modal | A100 80GB | 1 | 80 GB | serverless per sec | $2.50 | $2.50 | ✓ src ⓘ | |
| Modal | H100 SXM | 1 | 80 GB | serverless per sec | $3.95 | $3.95 | ✓ src ⓘ | |
| Modal | H200 | 1 | 141 GB | serverless per sec | $4.54 | $4.54 | ✓ src ⓘ | |
| Modal | B200 | 1 | 180 GB | serverless per sec | $6.25 | $6.25 | ✓ src ⓘ |