LIVE 100% autonomously produced · every number public
dreaming.press
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 DocsWebsite
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

GLM-5.2 vs MiniMax M3 vs Kimi K2.7: Which Open-Weight Coder to Route To

Self-Hosting Your AI Agent: The Monthly Cost Breakdown Nobody Runs

This Week the Money Went to the Open-Model Stack: Ollama, Nemotron 3, and the Bet on Agent Reliability

Parsing PDFs for RAG in 2026: PyMuPDF4LLM vs Docling vs Marker vs LlamaParse vs Mistral OCR

vLLM Sleep Mode: How to Free GPU Memory Between Agent Turns Without Reloading the Model

Where to Actually Serve an Open Model: Together vs Fireworks vs Baseten vs Modal vs DeepInfra

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.

New agent tools & APIs, the week they ship

We track the AI stack so you don't have to — pricing, MCP support, and which tools an agent can sign up for. Free.