The Stack · LLM gateways & inference API

Modal

Serverless GPU/CPU cloud where you define container + hardware in Python code and run per-second-billed inference, batch, and training jobs.

API keyFreemium🟡 agent: manual only

Get API key → human signup required Docs Website

CategoryLLM gateways & inference

TypeAPI service

Authapi-key

PricingFreemium

Agent signup🟡 manual only

SDKsPython, CLI

Pricing: Starter free with $30/mo credits; per-second GPU pricing (T4 to B200); Team plan $250/mo

🟡 Agents: manual only

Manual — signup needs a human (card, verification, or sales).

Account via GitHub/Google login, then tokens are created with the `modal token new` CLI (browser step) — human-in-the-loop; $30/mo free credits after

Modal — Serverless GPU/CPU cloud where you define container + hardware in Python code and run per-second-billed inference, batch, and training jobs.
Website: https://modal.com
Docs: https://modal.com/docs
Get a key: https://modal.com/signup
Agent signup: manual only — Account via GitHub/Google login, then tokens are created with the `modal token new` CLI (browser step) — human-in-the-loop; $30/mo free credits after
Auth: api-key
Pricing: freemium — Starter free with $30/mo credits; per-second GPU pricing (T4 to B200); Team plan $250/mo
Full record: https://dreaming.press/api/tools/modal.json

Machine record: /api/tools/modal.json

Quickstart

import modal
app = modal.App("hello")

@app.function(gpu="A100")
def generate(prompt: str):
    # load model + run inference on the GPU
    return prompt.upper()

@app.local_entrypoint()
def main():
    print(generate.remote("hello from a serverless GPU"))

python · full docs →

Modal in our coverage

Serverless GPU in 2026: What 'Scale to Zero' Really Means, and Where to Run It — Azure, Databricks, Modal, RunPod, Baseten

2026-09-11

LLM API Pricing Comparison, September 2026: The New Ceiling, the Cache-Read War, and the Promo Prices That Reset January 1

2026-09-09

Best LLM for Image Generation (September 2026): GPT Image 2 vs Nano Banana 2 vs FLUX.2 vs Seedream vs Midjourney

2026-09-05

The Founder's Wire, August 30: Anthropic's Priciest Model Stalled at 11% of Spend, OpenAI's Report Says 700 Test Agents Broke Out and Hacked Hugging Face, and Nine Days Brought Five Open-Weight Frontier Models

2026-08-30

How to Deploy an LLM Locally (2026): The Fastest Path, Model Picks, and an OpenAI-Compatible API

2026-08-30

The Founder's Wire, August 27: A Personal-Agent Startup Hit $2.5B in Weeks, Amazon Is Closing Mechanical Turk, and OpenAI's Own Chip Beat Nvidia on Efficiency

2026-08-27

Modal FAQ

What is Modal?

Modal is Serverless GPU/CPU cloud where you define container + hardware in Python code and run per-second-billed inference, batch, and training jobs. It's in the LLM gateways & inference category of the dreaming.press tool directory.

Is Modal free?

Modal is freemium — free to start, paid plans for scale. Starter free with $30/mo credits; per-second GPU pricing (T4 to B200); Team plan $250/mo.

Can an AI agent sign up for Modal automatically?

Not automatically — signup requires a human (a credit card, verification, or a sales conversation). Account via GitHub/Google login, then tokens are created with the `modal token new` CLI (browser step) — human-in-the-loop; $30/mo free credits after.

Does Modal have an MCP server?

Modal does not publish an official MCP server as of our last check.

Is Modal open source?

Modal is a hosted API service, not an open-source project.

What languages does Modal support?

Modal offers Python, CLI.