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: Open WebUI
providerId: open-webui
created: '2026-05-08'
# Provenance stamped 2026-08-11: this artifact was written by the API Evangelist
# bulk sweep dated 2026-05-08, not harvested from the provider. See roadmap#35.
method: generated
modified: '2026-05-08'
reconciled: true
tags:
- LLM
- Open Source
- Self-Hosted
- Ollama
- Chat UI
- RAG
- Rate Limiting
- Quotas
- Throttling
description: >-
  Open WebUI does not impose project-level API rate limits. Effective limits are determined by (1) the
  upstream LLM backend's limits (Ollama concurrency, or OpenAI/Anthropic RPM caps) and (2) any
  reverse-proxy or admin throttling configured in the deployment. Standard HTTP semantics apply.
notes: No built-in rate limits; effective limits come from upstream LLM and your reverse proxy.
sources:
- https://docs.openwebui.com/
- https://github.com/open-webui/open-webui
responseCodes:
  throttled: 429
limits:
- name: Project-level
  scope: n/a
  metric: n/a
  limit: no built-in cap
  notes: Open WebUI itself does not throttle; configure at reverse proxy if needed.
- name: Upstream LLM backend
  scope: external
  metric: requests
  limit: backend-defined
  notes: Ollama concurrency or OpenAI/Anthropic RPM caps apply.
policies:
- name: Reverse-Proxy Throttling
  description: Use Nginx/Caddy/Traefik in front of Open WebUI to enforce per-IP or per-user limits if needed.
- name: Backend Concurrency
  description: Tune Ollama OLLAMA_NUM_PARALLEL or OPENAI_API_BASE_URLS to spread load.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com