Agentic WeeklyGet the weekly
Open WebUIv0.12.4Tested (smoke test)

Open WebUI: what’s new in v0.12.4 and our verdict

Self-hosted AI platform: a web interface that connects to Ollama and OpenAI-compatible models, under its own Open WebUI License.

Official site

Release Ruler for Open WebUI: marked at its Tested release date on the timeline of every AI model we track.

At a glance

Evidence
Tested (smoke test)
Released
Oct 25, 2026
Last verified
Oct 25, 2026
Pricing
Partly verified
Best for
local LLM tools and model platforms

Evidence and ranking

Evidence behind this verdict

  1. Sources read3 cited sources, latest fetched Oct 25, 2026. (done)
  2. Facts re-checkedLast verified Oct 25, 2026. (done)
  3. Run by usSmoke test on Oct 25, 2026 (scope below). (done)

Passed Test log result: Passed. Read the log

Where we rank it (editorial)

Listed here but not yet ranked. Ranks are editorial picks, not benchmark scores.

Pricing: No pricing page read. (checked 2026-10-25)

Our verdict

Self-hosted AI platform: a web interface that connects to Ollama and OpenAI-compatible models, under its own Open WebUI License.

Good for

  • Teams that want a self-hosted chat UI
  • Ollama users who want a browser interface

Skip if

  • You need a standard OSI license for your own distribution

Tested. Tested 2026-10-25 (America/Chicago). Open WebUI 0.12.4 installed with uv in 11.6 s (6,977 MB in the virtualenv), was healthy about 11 to 12 s after start, and answered a chat through its API in 0.68 s using a local Ollama model. Test environment: Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key. Agent tools were pointed at a local open-weight model (Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11), so we tested the tool, not any vendor's hosted models. Not tested: The browser UI, RAG over documents, web search, multi-user roles, and Docker deployment; One request; a smoke test, not a load test. These are smoke tests, not a benchmark. Full log: /tests/open-webui.

Full test log with exact commands, versions and raw output: Open WebUI 0.12.4: our test log.

Evidence
Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)). A smoke test is not a benchmark.
What we ran
Open WebUI 0.12.4 installed with uv in 11.6 s (6,977 MB in the virtualenv), was healthy about 11 to 12 s after start, and answered a chat through its API in 0.68 s using a local Ollama model.
Model used
Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11
Environment
Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key
Not tested
The browser UI, RAG over documents, web search, multi-user roles, and Docker deployment; One request; a smoke test, not a load test.
Date
(America/Chicago)

Best for

Key facts

Open WebUI's site pitches a self-hosted AI platform you run on your own machine and connect to any model. The repository's license file is a custom 'Open WebUI License' (BSD-style terms with additional conditions), not a standard OSI license; v0.12.4 was tagged Oct 25, 2026.

  • License: Open WebUI License (custom; read it before commercial use)
  • Platforms: Self-hosted (Docker and others)
  • Pricing model: Free self-hosted
  • Free tier: Free to self-host
  • Paid plans: Enterprise options not read
  • GitHub: open-webui/open-webui: 156,757 stars on 2026-10-25, last push 2026-10-25
  • Latest release we saw: v0.12.4, 2026-10-25
  • How to start: Follow the install guide on openwebui.com (Docker is the common route) and connect a model backend.
  • v0.12.4 (2026-10-25): the newest release listed on the official page or repository when we read it on 2026-10-25.

How to set it up: Get started with Open WebUI

These steps come from the vendor's own pages as read on 2026-10-25. We ran Open WebUI on 2026-10-25; the test log lists what was and was not covered.

  1. Get access

    Follow the install guide on openwebui.com (Docker is the common route) and connect a model backend.

  2. Check the limits and costs first

    Free to self-host. Paid: Enterprise options not read. No pricing page read.

Pros and cons

Pros

  • Very active (v0.12.4 on Oct 25, 2026)
  • Large community

Cons

  • Custom license, not MIT or Apache
  • Our test was one small task on a local 3B model; it does not show behaviour with hosted models or larger jobs

Alternatives and comparisons

  • Ollama: The common way to run open models locally on macOS, Windows and Linux, with a cloud option and an MIT-licensed open-source core.
  • Jan: Open-source alternative to ChatGPT that runs open models locally or connects to cloud models like GPT and Claude.
  • Dify: Open-source platform for building LLM apps and agent workflows with a visual canvas; licensed under a modified Apache 2.0 with extra conditions.
  • Cohere: Enterprise AI company: Command models, Rerank and the North platform.

See all alternatives to Open WebUI

FAQ

What is Open WebUI?

Open WebUI's site pitches a self-hosted AI platform you run on your own machine and connect to any model. The repository's license file is a custom 'Open WebUI License' (BSD-style terms with additional conditions), not a standard OSI license; v0.12.4 was tagged Oct 25, 2026.

Is Open WebUI free?

Free to self-host. Paid: Enterprise options not read. No pricing page read. Checked 2026-10-25; prices change, so confirm on the vendor's page.

What license is Open WebUI under?

Its license: Open WebUI License (custom; read it before commercial use). Read from the project's own pages on 2026-10-25.

What we have not verified

  • Enterprise pricing

Sources

Last verified · Agentic Weekly

Latest news about Open WebUI

  • Cohere: Enterprise AI company: Command models, Rerank and the North platform.
  • DeepSeek: Model API that works with the OpenAI and Anthropic SDK formats and can back agent tools such as Claude Code, GitHub Copilot and OpenCode.
  • Hugging Face: The hub where the ML community shares models, datasets and apps, with PRO, Team and Enterprise tiers.

How to cite this page

Agentic Weekly, "Open WebUI v0.12.4: what's new, verdict & setup", last updated 2026-10-25, https://theagenticweekly.com/tools/open-webui

Keep the Reported or Tested label when you quote a verdict. Plain-text version: https://theagenticweekly.com/tools/open-webui.md. More for AI assistants: /ai, /tools.json, /llms.txt.