Open WebUI

Open WebUI is a self-hosted, open-source web UI for LLMs (notably Ollama and OpenAI-compatible backends). It exposes a REST API for chats, models, prompts, knowledge (RAG), users, and tools. Distributed under a modified BSD-3-Clause license; primarily run via Docker or pip on your own infrastructure.

1 APIs 0 Features

LLMOpen SourceSelf-HostedOllamaChat UIRAG

APIs

Open WebUI API

REST API exposed by a self-hosted Open WebUI instance. Endpoints cover chat completions (proxying upstream backends like Ollama or OpenAI-compatible servers), models, prompts, k...

Collections

Open WebUI API

OPEN

Pricing Plans

Open Webui Plans Pricing

1 plans

PLANS

Rate Limits

Open Webui Rate Limits

2 limits

RATE LIMITS

FinOps

Open Webui Finops

FINOPS

Resources

Sources

opencollection: 1.0.0
info:
  name: Open WebUI API
  version: 1.0.0
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Chat
    type: folder
  items:
  - info:
      name: Chat completions (OpenAI-compatible)
      type: http
    http:
      method: POST
      url: http://localhost:3000/api/chat/completions
      body:
        type: json
        data: '{}'
    docs: 'OpenAI-compatible chat completions endpoint that routes requests to the

      configured backend (Ollama, OpenAI-compatible, or local model).

      '
- info:
    name: Anthropic
    type: folder
  items:
  - info:
      name: Anthropic-compatible messages
      type: http
    http:
      method: POST
      url: http://localhost:3000/api/v1/messages
      body:
        type: json
        data: '{}'
    docs: Compatible with the Anthropic Messages API surface; usable with the Anthropic SDK and Claude Code.
- info:
    name: Ollama
    type: folder
  items:
  - info:
      name: List Ollama models (passthrough)
      type: http
    http:
      method: GET
      url: http://localhost:3000/ollama/api/tags
    docs: List Ollama models (passthrough)
  - info:
      name: Generate completion via Ollama (passthrough)
      type: http
    http:
      method: POST
      url: http://localhost:3000/ollama/api/generate
      body:
        type: json
        data: '{}'
    docs: Generate completion via Ollama (passthrough)
  - info:
      name: Chat via Ollama (passthrough)
      type: http
    http:
      method: POST
      url: http://localhost:3000/ollama/api/chat
      body:
        type: json
        data: '{}'
    docs: Chat via Ollama (passthrough)
bundled: true