specification: API Commons Rate Limits
specificationVersion: '0.1'
schema: https://raw.githubusercontent.com/api-evangelist/interface-research/main/schema/api-commons.yml#/$defs/RateLimits
provider: Chutes
providerId: chutes
created: '2026-06-21'
modified: '2026-06-21'
reconciled: false
tags:
- AI
- LLM
- Inference
- Serverless
- GPU
- Bittensor
- Rate Limiting
- Quotas
- Throttling
description: >-
  Chutes enforces per-account quotas and concurrency limits on public inference
  through llm.chutes.ai/v1, governed by available subnet capacity, the account's
  plan (pay-as-you-go vs. Plus/Pro monthly budget), and per-model availability.
  Free / subsidized models carry the tightest throttles. Private (dedicated)
  chutes are limited by the GPU capacity provisioned for the deployment rather
  than a shared quota. Specific per-model RPM/TPM values are not reconciled in
  this artifact.
notes: >-
  Verify per-model and per-plan limits in the Chutes dashboard during
  reconciliation; throttles shift with Bittensor Subnet 64 capacity and as
  accounts move between pay-as-you-go and monthly plans.
sources:
- https://chutes.ai/docs
- https://chutes.ai/pricing
- https://chutes.ai/docs/api-reference/overview
responseCodes:
  throttled: 429
limits:
- name: Requests Per Minute (RPM)
  scope: account
  metric: requests
  limit: see provider documentation
  notes: Per-model and per-plan; varies with subnet capacity.
- name: Tokens Per Minute (TPM)
  scope: account
  metric: tokens
  limit: see provider documentation
  notes: Per-model and per-plan; varies with subnet capacity.
- name: Concurrency
  scope: account
  metric: concurrent_requests
  limit: see provider documentation
  notes: Concurrent in-flight inference requests per account.
- name: Free / Subsidized Model Quota
  scope: account
  metric: requests
  limit: see provider documentation
  notes: Free and subsidized models carry tighter throttles than paid models.
- name: Monthly Budget Quota
  scope: account
  metric: spend
  limit: plan dependent
  notes: Plus/Pro monthly plans include a fixed budget; usage beyond it is discounted per-token.
- name: Private Chute Capacity
  scope: deployment
  metric: gpu_capacity
  limit: provisioned per deployment
  notes: Dedicated chutes are bounded by the GPU capacity provisioned, not a shared quota.
policies:
- name: Plan-Tiered Limits
  description: Quotas and budgets raise as accounts move from pay-as-you-go to Plus, Pro, and Enterprise plans.
- name: Subnet Capacity
  description: Public inference throughput depends on live Bittensor Subnet 64 miner capacity for the requested model.
- name: Backoff Strategy
  description: Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com