Chutes
Chutes serves open-source language, image, video and speech models through an OpenAI-style API and runs customers' own models on confidential GPUs.
What it does
- Model inference
- Model hosting
Features 3
- Serverless computeRuns inference on top open-source models plus ephemeral and batch processing jobs.
- Bring your own codeLets you bring your own code and run any open model with a few lines of code.
- Embedding modelsEmbedding models for search, recommendation and other uses of your data.
Sources
- Pricing
-
Pricing page: "Pay per token. No subscription, no minimum, no markup."
- Description
-
Official documentation · 10 Nov 2026
Product page: "High-performance AI Inference of top SOTA OSS Models, ephemeral jobs, batch processing jobs, and much more."
- What it does
-
Official documentation · 10 Nov 2026
Product page: "High-performance AI Inference of top SOTA OSS Models, ephemeral jobs, batch processing jobs, and much more."
- Sold within
-
Sold on its own with published plans.
- Name
-
Official documentation · 10 Nov 2026
Name as published on the product page.
- URL
-
Official documentation · 10 Nov 2026
Product page, read 2026-11-10.
- Deployment
-
Official documentation · 10 Nov 2026
Product page: "Pay for the tokens you use, or deploy your own chute on a confidential GPU and pay by the second."
- Interfaces
-
Official documentation · 10 Nov 2026
Product page: "Pay for the tokens you use, or deploy your own chute on a confidential GPU and pay by the second."
Also from Chutes
-
Custom Chutes Platform
Deploys a team's private or fine-tuned model on dedicated GPU capacity behind its own API endpoint, billed per second of GPU time plus a one-time deployment fee.
Something wrong here? Send a correction — quote this product id: chutes-platform.