[GH-ISSUE #24107] feat: Model comparison table with cost, context window, and replacement recommendations #58855

Closed
opened 2026-05-06 00:17:33 -05:00 by GiteaMirror · 6 comments
Owner

Originally created by @githb-ac on GitHub (Apr 24, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/24107

Check Existing Issues

  • I have searched for all existing open AND closed issues and discussions for similar requests. I have found none that is comparable to my request.

Verify Feature Scope

  • I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions.

Problem Description

When a user has multiple models configured across different providers in Open WebUI,
there is no single place to compare them side by side. Models are listed in the
model selector dropdown with no cost or capability metadata attached. Users running
multiple providers (Anthropic, OpenRouter, Ollama, etc.) have to manually
cross-reference external pricing pages to make informed decisions about which model
to use for a given task. There is no unified cost visibility within the UI.

Desired Solution you'd like

Add a Model Comparison table in Admin → Models showing all configured models with
the following columns:

| Model | Provider | Input cost (per 1M tokens) | Output cost (per 1M tokens) | Context window | Recommended alternative |

  • Costs pulled from provider API metadata where available, or manually entered
  • "Recommended alternative" column suggests a cheaper or higher-performing model
    for the same task category
  • Sortable by cost, context window, or provider
  • Works across all configured providers including local Ollama models (shown as $0.00)

Alternatives Considered

Currently the only alternative is manually cross-referencing provider pricing pages
(OpenRouter, Anthropic, etc.) in a separate browser tab. This is time-consuming
and error-prone, especially when managing more than 3-4 models across providers.

Additional Context

A working visual prototype of this table is attached to this issue.

owui-model-health-cost.html

Originally created by @githb-ac on GitHub (Apr 24, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/24107 ### Check Existing Issues - [x] I have searched for all existing **open AND closed** issues and discussions for similar requests. I have found none that is comparable to my request. ### Verify Feature Scope - [x] I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions. ### Problem Description When a user has multiple models configured across different providers in Open WebUI, there is no single place to compare them side by side. Models are listed in the model selector dropdown with no cost or capability metadata attached. Users running multiple providers (Anthropic, OpenRouter, Ollama, etc.) have to manually cross-reference external pricing pages to make informed decisions about which model to use for a given task. There is no unified cost visibility within the UI. ### Desired Solution you'd like Add a Model Comparison table in Admin → Models showing all configured models with the following columns: | Model | Provider | Input cost (per 1M tokens) | Output cost (per 1M tokens) | Context window | Recommended alternative | - Costs pulled from provider API metadata where available, or manually entered - "Recommended alternative" column suggests a cheaper or higher-performing model for the same task category - Sortable by cost, context window, or provider - Works across all configured providers including local Ollama models (shown as $0.00) ### Alternatives Considered Currently the only alternative is manually cross-referencing provider pricing pages (OpenRouter, Anthropic, etc.) in a separate browser tab. This is time-consuming and error-prone, especially when managing more than 3-4 models across providers. ### Additional Context A working visual prototype of this table is attached to this issue. [owui-model-health-cost.html](https://github.com/user-attachments/files/27065804/owui-model-health-cost.html)
Author
Owner

@pr-validator-bot commented on GitHub (Apr 24, 2026):

⚠️ Missing Issue Title Prefix

@githb-ac, your issue title is missing a prefix (e.g., bug:, feat:, docs:).

Please update your issue title to include one of the following prefixes:

  • bug: Bug report or error you've encountered
  • feat: Feature request or enhancement suggestion
  • docs: Documentation issue or improvement request
  • question: Question about usage or functionality
  • help: Request for help or support

Example: bug: Login fails when using special characters in password

<!-- gh-comment-id:4315680989 --> @pr-validator-bot commented on GitHub (Apr 24, 2026): # ⚠️ Missing Issue Title Prefix @githb-ac, your issue title is missing a prefix (e.g., `bug:`, `feat:`, `docs:`). Please update your issue title to include one of the following prefixes: - **bug**: Bug report or error you've encountered - **feat**: Feature request or enhancement suggestion - **docs**: Documentation issue or improvement request - **question**: Question about usage or functionality - **help**: Request for help or support Example: `bug: Login fails when using special characters in password`
Author
Owner

@Classic298 commented on GitHub (Apr 25, 2026):

Consider using model descriptions for this

<!-- gh-comment-id:4318585243 --> @Classic298 commented on GitHub (Apr 25, 2026): Consider using model descriptions for this
Author
Owner

@githb-ac commented on GitHub (Apr 25, 2026):

Thanks for the response — but model descriptions are free-text fields. They cannot create a sortable, structured comparison table showing input cost per 1M tokens, output cost per 1M tokens, context window size, and recommended alternatives across all configured providers simultaneously.

What's being requested is a data table in Admin → Models that gives users a unified cost and capability view across all their configured models — something that requires structured data, not free-text descriptions. Would appreciate reconsideration.

<!-- gh-comment-id:4318619565 --> @githb-ac commented on GitHub (Apr 25, 2026): Thanks for the response — but model descriptions are free-text fields. They cannot create a sortable, structured comparison table showing input cost per 1M tokens, output cost per 1M tokens, context window size, and recommended alternatives across all configured providers simultaneously. What's being requested is a data table in Admin → Models that gives users a unified cost and capability view across all their configured models — something that requires structured data, not free-text descriptions. Would appreciate reconsideration.
Author
Owner

@Classic298 commented on GitHub (Apr 25, 2026):

Would Tags solve it for you then? Standardized tags and you can sort and compare side by side in the model picker.

Either way belongs in discussions as a feat request not here

<!-- gh-comment-id:4319147349 --> @Classic298 commented on GitHub (Apr 25, 2026): Would Tags solve it for you then? Standardized tags and you can sort and compare side by side in the model picker. Either way belongs in discussions as a feat request not here
Author
Owner

@githb-ac commented on GitHub (Apr 25, 2026):

Tags in the model picker are labels — they let you categorise models but they cannot store or display structured numeric data like input cost per 1M tokens, output cost per 1M tokens, or context window size. The model picker also has no concept of sorting by cost or comparing two models on quantitative metrics side by side.

What's being requested is a structured data table with sortable numeric columns — something tags are architecturally incapable of providing. On the point about discussions: this was originally filed as a feature request in the correct section. If it belongs in discussions, could you convert it rather than close it, so the request stays visible and discoverable for others who may want the same thing?

<!-- gh-comment-id:4319542317 --> @githb-ac commented on GitHub (Apr 25, 2026): Tags in the model picker are labels — they let you categorise models but they cannot store or display structured numeric data like input cost per 1M tokens, output cost per 1M tokens, or context window size. The model picker also has no concept of sorting by cost or comparing two models on quantitative metrics side by side. What's being requested is a structured data table with sortable numeric columns — something tags are architecturally incapable of providing. On the point about discussions: this was originally filed as a feature request in the correct section. If it belongs in discussions, could you convert it rather than close it, so the request stays visible and discoverable for others who may want the same thing?
Author
Owner

@Classic298 commented on GitHub (Apr 25, 2026):

Yes i can convert

<!-- gh-comment-id:4319551414 --> @Classic298 commented on GitHub (Apr 25, 2026): Yes i can convert
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#58855