specification: API Commons Plans
specificationVersion: '0.1'
schema: https://raw.githubusercontent.com/api-evangelist/interface-research/main/schema/api-commons.yml#/$defs/Plans
provider: Chutes
providerId: chutes
created: '2026-06-21'
modified: '2026-06-21'
reconciled: false
tags:
- AI
- LLM
- Inference
- Serverless
- GPU
- Bittensor
- Plans
description: >-
  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.
notes: >-
  Representative rates as published on the Chutes pricing page; values are
  snapshots and change with Bittensor subnet economics. Verify the current model
  catalog, free-tier thresholds, and GPU hourly rates against the live pricing
  page during reconciliation.
sources:
- https://chutes.ai/pricing
- https://chutes.ai/docs
plans:
- id: chutes-pay-as-you-go
  name: Pay-as-you-go (Public Inference)
  type: usage
  description: >-
    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.
  entries:
  - label: Budget LLM (e.g. Mistral-Nemo-Instruct)
    name: llm_budget
    type: usage
    metric: tokens
    limit: -1
    timeFrame: month
    geo: global
    unit: 1000000
    price: ~$0.0245 input / ~$0.0978 output per 1M (varies by model)
    userMultiplied: false
  - label: Mid-range LLM (e.g. Gemma / Qwen3-32B)
    name: llm_mid
    type: usage
    metric: tokens
    limit: -1
    timeFrame: month
    geo: global
    unit: 1000000
    price: ~$0.10-$0.42 per 1M (varies by model)
    userMultiplied: false
  - label: Premium LLM (e.g. DeepSeek-V3.2 / GLM-5.2)
    name: llm_premium
    type: usage
    metric: tokens
    limit: -1
    timeFrame: month
    geo: global
    unit: 1000000
    price: up to ~$1.40 input / ~$4.40 output per 1M (varies by model)
    userMultiplied: false
  - label: Free / subsidized models
    name: llm_free
    type: usage
    metric: tokens
    limit: -1
    timeFrame: month
    geo: global
    unit: 1000000
    price: $0 for select models (subsidized by Bittensor TAO incentives)
    userMultiplied: false
  elements:
  - name: Chat Completions
  - name: Models Listing
  - name: Image / Diffusion (cords)
- id: chutes-private
  name: Private Chutes (Self-Serve Deployment)
  type: usage
  description: >-
    Dedicated AI workloads deployed on verified self-serve confidential (TEE) GPU
    capacity, billed per-second while running, with automatic idle shutdown.
  entries:
  - label: GPU Runtime (e.g. RTX Pro 6000)
    name: gpu_runtime
    type: usage
    metric: seconds
    limit: -1
    timeFrame: usage
    geo: global
    unit: 3600
    price: ~$1.80 per hour (billed per-second; varies by GPU)
    userMultiplied: false
  - label: Deployment Fee
    name: deployment_fee
    type: flat
    metric: deploys
    limit: -1
    timeFrame: usage
    geo: global
    unit: 1
    price: one-time ~$5.40 (3x hourly rate) per deployment
    userMultiplied: false
  elements:
  - name: Dedicated Chute Deployment
  - name: Confidential (TEE) GPU
- id: chutes-plus
  name: Plus
  type: subscription
  description: >-
    Optional monthly plan providing a fixed budget plus a discount on per-token
    rates beyond the included quota.
  entries:
  - label: Plus Monthly
    name: plus_monthly
    type: flat
    metric: subscription
    limit: -1
    timeFrame: month
    geo: global
    unit: 1
    price: ~$10/month, ~6% discount on per-token rates beyond quota
    userMultiplied: false
  elements:
  - name: Monthly Budget
  - name: Token Discount
- id: chutes-pro
  name: Pro
  type: subscription
  description: >-
    Optional monthly plan with a larger fixed budget and a higher discount on
    per-token rates beyond the included quota.
  entries:
  - label: Pro Monthly
    name: pro_monthly
    type: flat
    metric: subscription
    limit: -1
    timeFrame: month
    geo: global
    unit: 1
    price: ~$20/month, ~10% discount on per-token rates beyond quota
    userMultiplied: false
  elements:
  - name: Monthly Budget
  - name: Token Discount
- id: chutes-enterprise
  name: Enterprise
  type: enterprise
  description: >-
    Volume discounts and negotiated terms for large workloads. Contact Chutes.
  entries:
  - label: Enterprise Agreement
    name: enterprise
    type: flat
    metric: contract
    limit: -1
    timeFrame: year
    geo: global
    unit: 1
    price: contact sales
    userMultiplied: false
  elements:
  - name: Volume Discounts
  - name: Dedicated Capacity
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com