









Chutes is a decentralized serverless AI compute platform for deploying, running, and scaling open-source AI models through a web platform or API. It supports production inference, private confidential GPU workloads, and multiple modalities including image, video, speech, and music.
Create an account, pick a model from the catalog or use the API, and send requests with your CHUTES_API_KEY. For private workloads, build your container with the Chutes CLI, define the GPU requirements, and deploy the chute as a confidential instance.
Here is the Chutes support email for customer service: [email protected] . More Contact, visit the contact us page(https://chutes.ai/contact)
Chutes Company name: Chutes .
Chutes Company address: .
More about Chutes, Please visit the about us page().
Chutes Sign up Link: https://chutes.ai/signup
Chutes Pricing Link: https://chutes.ai/pricing
Chutes Twitter Link: https://twitter.com/chutes_ai
Chutes Github Link: https://github.com/chutesai

Pay-as-you-go
Varies by model
Public inference billed per 1M tokens with no subscription or minimum. Example rates include Mistral-Nemo-Instruct-2407 at $0.0245 in / $0.0978 out per 1M tokens and Qwen3-32B at $0.104 in / $0.416 out per 1M tokens.
Plus
$10 per month
Bundled daily quota with 6% off PAYG pricing beyond the quota.
Pro
$20 per month
Bundled daily quota with 10% off PAYG pricing beyond the quota.
Private Chute
From $1.80 per hour
Self-serve confidential GPU deployment with a one-time deployment fee starting at $5.40, equal to 3x the hourly rate.
Enterprise
Contact sales
Custom billing only, with volume discounts, custom rate limits, and dedicated support.
For the latest pricing, please visit this link: https://chutes.ai/pricing




Social Listening