ToolsCompaniesAbout

Chutes

by ChutesNo ratings yet

Serverless hosting for open-source AI models, billed per token or GPU second

Visit chutes.ai

Linked from chutes.ai · checked 29 Oct

Tool type
Open-source model hosting API
Made for
Developers and enterprise teams
Runs on
Chutes cloud GPU infrastructure, called via web, API, and CLI
Hosted models run on confidential TEE GPUs; private chutes run on self-serve TEE GPU capacity selected by the deployer.
Last checked
29 Oct 2026
4 product sources

From @chutes_ai

Recent important posts · features, availability

Open on X

What it does

Chutes takes in an API request naming an open-source model and a prompt, then returns generated output such as text, images, video, speech, or music. It also takes in your own container code for a private deployment and runs that code on dedicated, confidential GPU capacity. Developers call hosted models through an HTTP chat-completions endpoint, or deploy their own chute with the chutes command-line tool.

People mostly use Chutes as a backend for AI-powered products: the site highlights per-token access to newly released open-source models, streaming responses, and batch or ephemeral jobs. What sets it apart is the confidential (TEE) compute on the featured models and the option to pay per second for a private GPU. A consumer chat app called Chutes Chat is also offered.

Chutes suits developers and teams building on open-source models who want pay-as-you-go billing without a subscription. Access requires creating an account and topping up a balance; the FAQ states there is no free tier. Limits to weigh: per-token rates change live, monthly plans are no longer sold, and enterprise custom billing requires contacting sales.

What it can do

  • Serve top open-source LLMs through an OpenAI-style chat completions API with streaming
  • Run image, video, speech, and music models alongside text models
  • Run embedding models and content-moderation models
  • Deploy your own model or code as a private chute on confidential GPU capacity using the chutes CLI
  • Pay per token for hosted models and per second for private GPU instances

Before you choose

  • Per-token rates are shown live and differ by model; check the pricing page before estimating costs.
  • There is no free tier according to the FAQ; monthly plans are no longer sold and existing ones do not renew.
  • Private chute deployment costs a one-time fee of three times the hourly GPU rate plus per-second billing while running.

Listed under

Get started

Sign up, add balance, and call the API with a key; private deployments use the chutes CLI.

  1. Create an account at chutes.ai and top up your balance in the app.
  2. Create an API key and set it as the CHUTES_API_KEY environment variable.
  3. Send requests to the chat completions endpoint at llm.chutes.ai using a model ID from the model list.
Create an account and top up balance

Plans and prices

Prices in USD

Hosted models bill per million input, cached-input, and output tokens; private chutes bill per second at the GPU hourly rate plus a one-time deployment fee of 3x the hourly rate. Enterprise plans are custom. Rates are live and change.

Pay as you go (tokens)Usage-basedNamed meters vary by model; see the pricing page for per-model rates. Example snapshot: Gemma 4 31B turbo lists $0.12 input and $0.37 output per 1M tokens.
  • No subscription or monthly commitment
  • Live per-token rates for every hosted model
Private Chutes (GPU)$2.25 per GPU hour (RTX Pro 6000)Billed per second while running. One-time deployment fee equals 3x the hourly rate (listed as $6.75).
  • Per-second GPU billing for private chutes
  • Isolated confidential GPU deployments
EnterpriseCustomCustom billing only; contact sales.
  • Volume discounts
  • Custom rate limits and dedicated support

Source: chutes.ai/pricing, checked 29 Oct 2026. Prices can change; check before you buy.

Sources for this overview

Product pages, documentation, and pricing checked 29 Oct 2026. Each source supports part of the overview; availability and prices can change.

Ratings and reviews

No ratings for Chutes yet.

Be the first to rate it

What’s changed

Free account

See what’s changed at Chutes

Launches, price moves and pivots, each with a date and a source. Free with an account.

Signals

Free account

See Chutes’s signals

Launch traction, hiring and release activity, tracked over time. Free with an account.

Data and security

Free account

See how Chutes handles your data

Training on your files, compliance, hosting and the models behind it. Free with an account.

Compare with similar tools

Free account

Compare Chutes side by side

Prices, platforms and features against similar tools, with sources. Free with an account.

Where this comes from

How we research
Company website
chutes.ai: product, pricing and policy pages
YC directory mirror
Batch and company name
Social accounts
Accounts the company links, and its posts on X
Human review
Checked by a person
knowledge_base
manual_review

Last checked 29 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.