M

Modal Inference

Infrastructure service

by Modal

Serve, scale and optimise model inference on Modal's runtime, with sub-second cold starts and autoscaling across regions.

Find alternatives to Modal Inference

Metered per second of compute on Modal's one rate card — Nvidia B200 $0.001736/sec, H200 SXM $0.001261/sec, H100 SXM5 $0.001097/sec, A100 80GB $0.000694/sec — with $30 a month of free compute. The products are not priced separately.

What it does

• Model inference
• Model hosting

How it compares

• Baseten Model APIs

  Modal differentiates through sub-second cold starts and pure Python integration, while competitors like Baseten rely on REST APIs or YAML configurations.

  Research report · 19 Sep 2026

Sources

Pricing

Pricing page · 5 Sep 2026

Metered per second of compute on Modal's one rate card — Nvidia B200 $0.001736/sec, H200 SXM $0.001261/sec, H100 SXM5 $0.001097/sec, A100 80GB $0.000694/sec — with $30 a month of free compute. The pro

Description

Official documentation · 5 Sep 2026

Modal's own product page for it, fetched 2026-09-05, HTTP 200.

Sold within

Official documentation · 5 Sep 2026

Modal's pricing page prices compute, not products: every one of the six entries in its Products nav runs on the same account and the same meter.

Also from Modal

• Modal Infrastructure service

  Serverless GPU compute: a Python decorator puts a function on an accelerator, scales it from zero to thousands of containers and stops billing when it stops running — aimed at inference, fine-tuning and batch jobs rather than reserved clusters.

• Modal Training Infrastructure service

  Managed training runs on Modal's fleet, configured in Python alongside the rest of a team's code.

• Modal Sandboxes Infrastructure service

  Isolated, instantly-started containers for running untrusted or agent-generated code at scale — the primitive behind AI app-generation products.

• Modal Notebooks Developer tool

  Hosted notebooks backed by Modal's GPUs, for profiling and experimenting without provisioning a machine.

• Modal Batch Infrastructure service

  Batch execution of large jobs across Modal's fleet, described as one line of code on the product page.

Open Modal in the directory

Something wrong here? Send a correction — quote this product id: modal-inference.