Whizi Model Finder
Whizi v1.0.0
Pick the right AI model
Competitor profile
Developer declarations; not independently tested. Listing last checked Nov 4, 2026. Package observed Nov 3, 2026.
Declared capabilities
- Read
Declared limitations
- Doing the task itself, not choosing a model. The plugin only recommends models, so ChatGPT should answer directly.
- Unrelated question. Nothing about AI models, so the plugin should not be called.
- Asks for an image to be generated. The plugin cannot run models or create images, so ChatGPT should handle it without calling the plugin.
Not specified in the available declarations: pricing & account requirements.
Onboarding example
Which AI model is best for coding, and which is cheapest?
Description
From the marketplace listing
Whizi Model Finder tells you which AI model to use for a job, and how named models compare. Ask which model is best for coding, writing, long documents, screenshots, math, data analysis, image generation or high-volume work, and it returns three picks: best quality, best value and lowest cost. Each pick shows the list price per million tokens, the context window and a one-line reason drawn from public leaderboards and the providers' own launch numbers. Ask about a language and the picks come from the Whizi Multilingual LLM Bench, which measures models in 30 languages including Arabic, Hindi, Japanese, Persian and Vietnamese. Name two to four models and it compares them side by side: price, context window, image input, multilingual score and the tasks Whizi recommends each for. It is read-only. It needs no account, sends nothing to an AI provider and stores nothing you ask. Every card links to the full model page on whizi.io.
Language: English · Automatically detected from descriptions.
Screenshots
From the developer.
Changes
No changes recorded yet. Follow this plugin to keep track of future changes.
First seen Nov 3, 2026. Last seen Nov 4, 2026.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Choose a model or agent route by quality, risk, capability, and cost before execution.
Shared terms: pick, model, cost, job
-
Ask another AI model a question, or ask two or three at once and see their answers side by side, using your llmwise account.
Shared terms: model, come, side, three
-
Realtime inference API for open-source models in your agent: two LLMs, text-to-speech and speech-to-text. Try the latest open-source mode...
Shared terms: model, cost, llms, per
-
Turns rough drafts into clear, structured prompts and recommends an AI model, tool and effort level for the task, across 15 AI platforms....
Shared terms: model, coding, line, reason
-
Guides you through running a quantized language model on your own Apple Silicon Mac with mlx-optiq.
Shared terms: model, long, pick, quality
Keywords
Files & skills
File archives
Release notes
First release. Two read-only tools: recommend_model (three picks for a task or language) and compare_models (two to four named models side by side), each rendered as a card.
Declared in the saved package. Remote tools may change independently.
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
- Package license
- UNLICENSED
- Package author
- Whizi
- Keywords
- See keywords
- Review scenarios
- 5 positive · 3 negativeScenario counts, not test results.
Declared capabilities
- Read
Package observed Nov 3, 2026.
Technical details
- First seen
- Nov 3, 2026 · 06:00 UTC
- Last seen
- Nov 4, 2026 · 00:00 UTC
- Collection status
- Collected
plugin_asdk_app_6ad4f8ffb48c81919d39990ca5a3df56
Download plugin data (JSON)