[PR #1347] [MERGED] docs: refresh model names and reframe model requirements as minimums #1322

New issue

Closed

opened 2026-10-18 14:18:51 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-18 14:18:51 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/docs/pull/1347
Author: @Classic298
Created: 8/10/2026
Status: ✅ Merged
Merged: 8/10/2026
Merged by: @Classic298

Base: main ← Head: claude/docs-model-names-audit-1y4kad

📝 Commits (2)

a5b676c docs: refresh model names and reframe model requirements as minimums
7118729 docs: modernize remaining model names in prose and API examples

📊 Changes

53 files changed (+274 additions, -243 deletions)

View changed files

📝 docs/alternatives/chatgpt.mdx (+5 -5)
📝 docs/alternatives/claude.mdx (+2 -2)
📝 docs/alternatives/gemini.mdx (+4 -4)
📝 docs/alternatives/ollama.mdx (+1 -1)
📝 docs/ecosystem/computer/ai/coding-agents.md (+1 -1)
📝 docs/ecosystem/computer/ai/connect-a-model.md (+2 -2)
📝 docs/faq.mdx (+5 -5)
📝 docs/features/administration/analytics/index.mdx (+1 -1)
📝 docs/features/administration/evaluation/index.mdx (+1 -1)
📝 docs/features/channels/index.md (+5 -5)
📝 docs/features/chat-conversations/audio/speech-to-text/mistral-voxtral-integration.md (+9 -5)
📝 docs/features/chat-conversations/audio/speech-to-text/openai-stt-integration.md (+8 -6)
📝 docs/features/chat-conversations/audio/text-to-speech/mistral-tts-integration.md (+10 -6)
📝 docs/features/chat-conversations/chat-features/autocomplete.md (+4 -5)
📝 docs/features/chat-conversations/chat-features/code-execution/python.md (+1 -1)
📝 docs/features/chat-conversations/chat-features/multi-model-chats.mdx (+2 -2)
📝 docs/features/chat-conversations/chat-features/reasoning-models.mdx (+4 -4)
📝 docs/features/chat-conversations/data-controls/import-export.md (+4 -4)
📝 docs/features/chat-conversations/image-generation-and-editing/gemini.mdx (+9 -9)
📝 docs/features/chat-conversations/image-generation-and-editing/lumenfall.md (+2 -2)

...and 33 more files

📄 Description

Replace retired and stale model identifiers across the docs, and rewrite
the "quality models required" callouts so they describe a minimum tier
rather than implying a frontier model is necessary.

Retired or shutting-down models that would fail for users today:

Groq removed llama-3.3-70b-versatile and llama-3.1-8b-instant
(shutdown 2026-08-16); point at gpt-oss and compound instead.
DeepSeek retired the deepseek-chat and deepseek-reasoner aliases
(2026-07-24); use deepseek-v4-pro / deepseek-v4-flash.
Mistral no longer publishes -latest aliases; use dated IDs
(voxtral-mini-2602, voxtral-tts-26-03, mistral-large-3-25-12,
mistral-small-4-0-26-03, codestral-25-08).
claude-3-opus, gpt-4, gpt-3.5-turbo, o3-mini and o4-mini are retired
or long superseded.
gemini-2.0-flash-exp is shut down; gemini-3-pro-image-preview is now
GA as gemini-3-pro-image.

The model requirement callouts previously named frontier models, which
overstated the bar and could lead users to believe a working setup was
underpowered. Agentic tool calling needs a current model, not an
expensive one, so these now name cheap and local options (GPT-5.6 Luna,
Gemini 3.5 Flash-Lite, MiniMax M3, DeepSeek V4 Flash, Qwen 3.6 27B,
Muse Glimmer 30B) and state plainly that the list is not continuously
maintained and that any recent model will do. Open Terminal keeps a
top-tier recommendation, since multi-step terminal work genuinely
benefits from it, but now also states a practical minimum.

Llama model references are replaced with current alternatives; llama.cpp
runtime references are untouched. Documented backend defaults such as
whisper-1 and mistral-tts-latest are left stated as-is, with a caution
where the upstream alias no longer resolves.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/docs/pull/1347 **Author:** [@Classic298](https://github.com/Classic298) **Created:** 8/10/2026 **Status:** ✅ Merged **Merged:** 8/10/2026 **Merged by:** [@Classic298](https://github.com/Classic298) **Base:** `main` ← **Head:** `claude/docs-model-names-audit-1y4kad` --- ### 📝 Commits (2) - [`a5b676c`](https://github.com/open-webui/docs/commit/a5b676c2dc993ce47476a03980b241c41ea872b8) docs: refresh model names and reframe model requirements as minimums - [`7118729`](https://github.com/open-webui/docs/commit/711872989169dd185ed1f5e09bb460cb8a69cc89) docs: modernize remaining model names in prose and API examples ### 📊 Changes **53 files changed** (+274 additions, -243 deletions) <details> <summary>View changed files</summary> 📝 `docs/alternatives/chatgpt.mdx` (+5 -5) 📝 `docs/alternatives/claude.mdx` (+2 -2) 📝 `docs/alternatives/gemini.mdx` (+4 -4) 📝 `docs/alternatives/ollama.mdx` (+1 -1) 📝 `docs/ecosystem/computer/ai/coding-agents.md` (+1 -1) 📝 `docs/ecosystem/computer/ai/connect-a-model.md` (+2 -2) 📝 `docs/faq.mdx` (+5 -5) 📝 `docs/features/administration/analytics/index.mdx` (+1 -1) 📝 `docs/features/administration/evaluation/index.mdx` (+1 -1) 📝 `docs/features/channels/index.md` (+5 -5) 📝 `docs/features/chat-conversations/audio/speech-to-text/mistral-voxtral-integration.md` (+9 -5) 📝 `docs/features/chat-conversations/audio/speech-to-text/openai-stt-integration.md` (+8 -6) 📝 `docs/features/chat-conversations/audio/text-to-speech/mistral-tts-integration.md` (+10 -6) 📝 `docs/features/chat-conversations/chat-features/autocomplete.md` (+4 -5) 📝 `docs/features/chat-conversations/chat-features/code-execution/python.md` (+1 -1) 📝 `docs/features/chat-conversations/chat-features/multi-model-chats.mdx` (+2 -2) 📝 `docs/features/chat-conversations/chat-features/reasoning-models.mdx` (+4 -4) 📝 `docs/features/chat-conversations/data-controls/import-export.md` (+4 -4) 📝 `docs/features/chat-conversations/image-generation-and-editing/gemini.mdx` (+9 -9) 📝 `docs/features/chat-conversations/image-generation-and-editing/lumenfall.md` (+2 -2) _...and 33 more files_ </details> ### 📄 Description Replace retired and stale model identifiers across the docs, and rewrite the "quality models required" callouts so they describe a minimum tier rather than implying a frontier model is necessary. Retired or shutting-down models that would fail for users today: - Groq removed llama-3.3-70b-versatile and llama-3.1-8b-instant (shutdown 2026-08-16); point at gpt-oss and compound instead. - DeepSeek retired the deepseek-chat and deepseek-reasoner aliases (2026-07-24); use deepseek-v4-pro / deepseek-v4-flash. - Mistral no longer publishes -latest aliases; use dated IDs (voxtral-mini-2602, voxtral-tts-26-03, mistral-large-3-25-12, mistral-small-4-0-26-03, codestral-25-08). - claude-3-opus, gpt-4, gpt-3.5-turbo, o3-mini and o4-mini are retired or long superseded. - gemini-2.0-flash-exp is shut down; gemini-3-pro-image-preview is now GA as gemini-3-pro-image. The model requirement callouts previously named frontier models, which overstated the bar and could lead users to believe a working setup was underpowered. Agentic tool calling needs a current model, not an expensive one, so these now name cheap and local options (GPT-5.6 Luna, Gemini 3.5 Flash-Lite, MiniMax M3, DeepSeek V4 Flash, Qwen 3.6 27B, Muse Glimmer 30B) and state plainly that the list is not continuously maintained and that any recent model will do. Open Terminal keeps a top-tier recommendation, since multi-step terminal work genuinely benefits from it, but now also states a practical minimum. Llama model references are replaced with current alternatives; llama.cpp runtime references are untouched. Documented backend defaults such as whisper-1 and mistral-tts-latest are left stated as-is, with a caution where the upstream alias no longer resolves. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-18 14:18:51 +00:00