AI inference

Chutes

Serverless AI compute platform for running open-source LLMs, image, video, and audio models at scale

chutes.ai

Verified API available Works with n8n ~1.3k monthly visits

Quick facts
What is it	Serverless AI compute platform for running open-source LLMs, image, video, and audio models at scale
Pricing	Paid — from $10/mo
Free tier	No
Platform	Web Application
API	Yes
Works with	n8n
Best for	deploying and scaling open-source LLMs for production, running image, video, and speech generation models
Domain registered	2024

Data updated Aug. 1, 2026

What does Chutes do?

Chutes is a serverless compute platform built for deploying and scaling open-source AI models. It handles everything from large language models to image generation, video processing, speech synthesis, and music creation. The service is designed for developers and teams who need reliable, on-demand AI inference without managing their own infrastructure. Chutes runs models in ephemeral, hot instances that stay ready to scale, so cold starts aren't a problem.

The platform works by letting you choose from hundreds of pre-deployed models or bring your own code. You get per-token or per-hour pricing depending on the model type. Chutes also offers TEE (Trusted Execution Environment) compute for secure, isolated jobs. A unique selling point is how quickly new open-source models appear here — often within minutes of release. There's a chat interface and a search tool for end users, but the core value is for developers using the Python SDK or API.

Chutes is best for AI developers, researchers, and product teams who want to run open-source models without provisioning GPUs or managing Kubernetes. If you're building an AI-powered app and need scalable inference for LLMs, image generation, or content moderation, this is a solid option. The pay-as-you-go model and monthly subscription tiers make it flexible for different usage levels.

AI API AI inference Developer Tools LLM

#agentic ai#ai model hosting#api access#batch processing#bittensor#confidential compute#content moderation#custom code deployment#decentralized-compute#embedding models#ephemeral jobs#gpu inference#image generation#llm inference#model-catalog#music generation#no cold starts#open-source ai models#pay-as-you-go pricing#per-token billing#private gpu deployment#production inference#scalable ai infrastructure#serverless ai compute#speech ai#tee#video generation#web platform

Key features

What makes it stand out

Hundreds of open-source models available for immediate use, including LLMs, image, video, speech, and music

TEE secure compute for private and isolated inference workloads

Pay-as-you-go pricing with per-token and per-hour rates, plus subscription plans for cost savings

Python SDK and API for integrating AI inference into applications

New open-source models added shortly after release

Who is Chutes for?

Who benefits most from this tool

deploying and scaling open-source LLMs for production

running image, video, and speech generation models

processing batch AI inference jobs

Pricing

Public Inference

Custom

0.0245 - 1.40 input per 1M tokens
0.0978 - 4.40 output per 1M tokens
Per-token pricing
No minimum
No markup

Private Chute

$5.40 one-time

1.8 hourly rate
Per-second billing
One-time deployment fee
Confidential GPU

Plus

$10.0/month

unknown daily quota
6% discount on payg
Bundled daily quota
6% off PAYG rates beyond the quota

Pro

$20.0/month

unknown daily quota
10% discount on payg
Larger daily quota
10% off PAYG rates beyond the quota

Enterprise

Custom

Volume discounts
Custom rate limits
Dedicated support

Trust & presence

Domain Domain registered 2024

Gallery

Click any image to enlarge

Alternatives in AI inference

Inferless AI inference

Serverless GPU platform for deploying machine learning models in minutes, with auto-scaling and pay-per-use pricing.

Baseten AI inference

AI infrastructure platform — deploy, serve, and scale machine learning models in production with optimized inference

n8n Top 100k site

Crusoe AI inference

Renewable-powered cloud infrastructure and managed inference service for running large AI models.

Superlinked AI inference

Self-hosted AI inference engine for search and document processing — deploy models on your own cloud infrastructure.

General Compute AI inference

High-speed AI inference API powered by purpose-built hardware, not repurposed GPUs.

Parasail.io AI inference

A global GPU network for running AI models at scale — serverless, dedicated, or batch inference with pay-per-token pricing.

Vast ai AI inference

Rent high-performance GPUs on demand for AI, machine learning, and graphics rendering at significantly lower costs.

Top 100k site

fireworks.ai AI inference

High-performance AI inference platform — deploy and scale open-source models like Llama and Gemma with a single API call.

Works with n8n

View all →

OpenAI Models

AI platform offering ChatGPT for conversation, an API for developers, and business solutions — all powered by GPT models.

n8n · integrately Top 1k site

DeepL Translator Translation

AI-powered translation tool delivering superior accuracy for text, documents, and real-time communication across 30+ languages.

n8n Top 1k site

Anthropic Models

AI research and product company building safe, capable assistants like Claude

zapier · n8n+3 Top 1k site

ClickUp AI Workspace

AI-powered project management hub — manage tasks, documents, and collaboration with built-in AI assistants.

zapier · n8n+1 Top 10k site

VEED.IO Video Editor

Online video editor with AI tools for subtitles, dubbing, avatars, and screen recording — all in your browser.

n8n Top 10k site

Claude AI Chat & Assistants

AI assistant that helps with writing, coding, analysis, and research — chat, generate content, or connect it to your tools

n8n · ifttt

JetBrains Developer Tools

A suite of integrated development environments (IDEs) with built-in AI coding assistance for multiple programming languages.