Modal review

Modal is the most flexible option here because you serve models with your own Python code instead of picking from a catalog. You define a function, attach a GPU, and Modal scales containers up and down with request volume, billing GPU, CPU and memory by the second. An H100 costs $0.001097 per second and an L4 $0.000222, and you pay nothing while no container runs. The Starter plan is $0 plus compute and includes $30 of free credits each month, three seats and 10 GPU concurrency. Team costs $250 a month plus compute, includes $100 of credits and raises limits to 50 GPU concurrency and 30 days of log retention. Modal also offers model endpoints for popular open models, sandboxes for agents and training. The trade-off is effort: you choose the engine, handle cold starts and maintain the code, which per-token APIs do for you.

Who it is for

Python teams that want to serve their own models with custom code and pay only while containers run.

Price

Starter $0 plus compute with $30 a month in free credits; Team $250 a month plus compute; H100 at $0.001097 per second.

$250 + compute / month
Quoted from the vendor pricing page on November 7, 2026.

Key features

• GPU, CPU and memory billed per second with no charge for idle resources
• GPUs from Nvidia T4 to B300
• Automatic scale up and down with request volume
• Web functions, scheduled functions and volumes
• Sandboxes for coding agents and untrusted code

Strengths and weaknesses

• Strength: $30 a month of free compute on the Starter plan
• Strength: No payment for idle GPUs between requests
• Strength: Committed spend can run through the AWS and GCP marketplaces
• Weakness: You write and maintain the serving code yourself
• Weakness: Team plan costs $250 a month before compute
• Weakness: Starter allows 10 GPU concurrency and 1 day of log retention

Key facts

• Nvidia H100: $0.001097 per second
• Nvidia L4: $0.000222 per second
• Starter credits: $30 a month
• Team plan: $250 a month plus compute, $100 credits

Where it ranks

Modal is No. 5 in our Best AI Inference Platforms verdict.