Chutes Plans Pricing
Chutes uses transparent, pay-as-you-go pricing with no required subscription. Public LLM inference is billed per-token at per-model rates (some open-source models are free, others heavily discounted because compute is subsidized by Bittensor TAO incentives on Subnet 64). Private chutes are dedicated, deployed on confidential (TEE) GPU capacity and billed per-second of runtime plus a one-time deployment fee. Optional monthly plans add a fixed budget plus a discount on per-token rates beyond the included quota. Specific per-model rates fluctuate with subnet economics and are not reconciled in this artifact.
Chutes Plans Pricing is the machine-readable pricing-plan profile for Chutes on the APIs.io network, conforming to the API Commons Plans specification.
It defines 5 plans, covering usage, subscription, and enterprise tiers, with named plans including Pay-as-you-go (Public Inference), Private Chutes (Self-Serve Deployment), Plus, Pro, Enterprise.
Tagged areas include AI, LLM, Inference, Serverless, and GPU.
Plans
Per-token, per-model inference across hundreds of open-source models at the shared llm.chutes.ai/v1 endpoint, with no monthly minimum and no markup tier.
- Chat Completions
- Models Listing
- Image / Diffusion (cords)
Dedicated AI workloads deployed on verified self-serve confidential (TEE) GPU capacity, billed per-second while running, with automatic idle shutdown.
- Dedicated Chute Deployment
- Confidential (TEE) GPU
Optional monthly plan providing a fixed budget plus a discount on per-token rates beyond the included quota.
- Monthly Budget
- Token Discount
Optional monthly plan with a larger fixed budget and a higher discount on per-token rates beyond the included quota.
- Monthly Budget
- Token Discount
Volume discounts and negotiated terms for large workloads. Contact Chutes.
- Volume Discounts
- Dedicated Capacity