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: Modal
providerId: modal-labs
created: '2026-07-01'
modified: '2026-07-01'
reconciled: false
tags:
- Serverless
- Compute
- GPU
- AI Infrastructure
- Rate Limiting
- Quotas
- Concurrency
description: >-
  Modal governs usage through concurrency limits rather than classic
  requests-per-minute API throttling, because the developer surface is an
  SDK/gRPC control plane and user-deployed containers, not a metered REST
  API. The key limits are concurrent containers and concurrent GPUs, which
  scale by subscription tier. User-deployed web endpoints (*.modal.run) scale
  by container concurrency; any request-level rate limiting on those endpoints
  is defined by the developer's own function code.
notes: >-
  Concurrency limits shown are the published per-tier defaults; Enterprise
  raises them via negotiated agreement. Verify current values on the Modal
  pricing page and in the workspace dashboard.
sources:
- https://modal.com/pricing
- https://modal.com/docs/guide/concurrent-inputs
- https://modal.com/docs/guide/scale
responseCodes:
  throttled: 429
limits:
- name: Concurrent Containers (Starter)
  scope: workspace
  metric: containers
  limit: 100
  notes: Maximum simultaneously running containers on the Starter tier.
- name: Concurrent GPUs (Starter)
  scope: workspace
  metric: gpus
  limit: 10
  notes: Maximum simultaneously attached GPUs on the Starter tier.
- name: Concurrent Containers (Team)
  scope: workspace
  metric: containers
  limit: 1000
  notes: Maximum simultaneously running containers on the Team tier.
- name: Concurrent GPUs (Team)
  scope: workspace
  metric: gpus
  limit: 50
  notes: Maximum simultaneously attached GPUs on the Team tier.
- name: Concurrent Containers / GPUs (Enterprise)
  scope: workspace
  metric: containers
  limit: negotiated
  notes: Higher GPU and container concurrency under an Enterprise agreement.
- name: Web Endpoint Request Rate
  scope: function
  metric: requests
  limit: user-defined
  notes: >-
    *.modal.run endpoints scale with container concurrency; any per-request
    rate limiting is implemented in the developer's own function code.
policies:
- name: Autoscaling
  description: >-
    Modal autoscales containers up to the workspace concurrency limit and
    scales to zero when idle; excess demand queues rather than being rejected.
- name: Tiered Concurrency
  description: Container and GPU concurrency ceilings raise from Starter to Team to Enterprise.
- name: Backoff Strategy
  description: >-
    SDK/CLI clients should implement exponential backoff with jitter and honor
    Retry-After on any 429 from the control plane.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com