AI Model Discovery Timeline: User Guide¶

Table of Contents¶

What is the Discovery Timeline?
Getting Started
Navigating the Timeline
Using Filters
Understanding Event Cards
Community Insights
FAQ
Troubleshooting
Providing Feedback
Appendix

What is the Discovery Timeline?¶

The AI Model Discovery Timeline is Magieva's feed of AI model discoveries, pricing changes, and capability updates from major providers such as OpenAI, Anthropic, Google, AWS, and others.

Why use it? - Stay informed: Keep track of important AI model updates without checking every provider individually. - Compare providers: See pricing changes across providers in one place. - Plan ahead: Know when models are updated or retired. - Learn from the community: Read tips and best practices shared by other users.

Example events you might see: - OpenAI launches a new model - Anthropic changes Claude pricing - Google Gemini adds a new capability, such as image generation - AWS Bedrock deprecates an older model version

Getting Started¶

Accessing the Discovery Timeline¶

Log in to Magieva at https://app.magieva.com.
Click Discovery in the left sidebar, located between Conversations and Integrations.
You'll see the timeline populated with the latest AI model events.

First-time users: The timeline may appear empty shortly after your account is created, since new events are collected on a regular schedule. Check back a little later if you don't see events right away.

System Requirements¶

Browser: A recent version of Chrome, Firefox, Safari, or Edge.
Internet: A stable connection, since timeline events load as you scroll.
Permissions: A standard Magieva user account — no special permissions are required.

Navigating the Timeline¶

Timeline Layout¶

The Discovery Timeline has three main sections:

┌─────────────────────────────────────────────────┐
│  Header (Title + Description)                   │
├─────────────────────────────────────────────────┤
│  Filters (Provider, Event Type, Search)         │
├─────────────────────────────────────────────────┤
│                                                  │
│  Event Cards (infinite scroll)                  │
│  ┌────────────────────────────────────────┐    │
│  │ [Provider Icon] OpenAI                 │    │
│  │ Model Discovered • 2 hours ago         │    │
│  │ GPT-5 launched with 10M context window │    │
│  └────────────────────────────────────────┘    │
│  ┌────────────────────────────────────────┐    │
│  │ [Provider Icon] Anthropic              │    │
│  │ Pricing Change • 5 hours ago           │    │
│  │ Claude 3.5 Sonnet reduced to $3/1M tok │    │
│  └────────────────────────────────────────┘    │
│                                                  │
│  [More events load automatically as you scroll] │
└─────────────────────────────────────────────────┘

Infinite Scroll¶

Events load automatically as you scroll down the page: - The timeline first loads a batch of recent events. - Additional events load automatically as you approach the bottom of the page. - All historical events are available — keep scrolling to go further back in time.

Tip: Scroll slowly for smooth loading. Very fast scrolling can trigger several loads at once and may briefly slow the page down.

Using Filters¶

Filters help you narrow the timeline down to specific providers, event types, or search terms.

Provider Filter¶

What it does: Shows only events from a specific AI provider.

How to use it: 1. Click the Provider dropdown (default: "All Providers"). 2. Select a provider from the list, for example: - OpenAI - Anthropic - Google - AWS (Bedrock) - Azure (OpenAI Service) - Cohere - Mistral - AI21 Labs - Replicate - Hugging Face 3. The timeline updates automatically.

Example: Select "Anthropic" to see only Claude model updates.

Event Type Filter¶

What it does: Shows only specific types of events.

How to use it: 1. Click the Event Type dropdown (default: "All Events"). 2. Select an event type: - Model Discovered: New AI models launched. - Pricing Change: Price increases or decreases. - Capability Update: New features, modalities, or capabilities. - Model Deprecated: Models being retired. - API Version Change: API breaking changes or new versions. 3. The timeline updates automatically.

Example: Select "Pricing Change" to see only pricing updates.

What it does: Searches across model names, providers, and event descriptions.

How to use it: 1. Click the Search box. 2. Type your query (for example, "GPT-4", "image generation", or "price"). 3. Results update automatically shortly after you stop typing.

Search tips: - Model names: "GPT-4", "Claude 3.5", "Gemini Pro" - Capabilities: "vision", "audio", "multimodal" - Pricing terms: "free tier", "discount", "price increase" - Providers: "OpenAI", "Google", "Anthropic"

Example: Search "vision" to find all models with vision capabilities.

Combining Filters¶

You can use multiple filters together:

Example 1: Provider = "OpenAI" + Event Type = "Pricing Change" → shows only OpenAI pricing changes.
Example 2: Search = "audio" + Event Type = "Capability Update" → shows only capability updates related to audio.

Clear filters: Click Clear All, or reload the page.

Understanding Event Cards¶

Each event card summarizes an AI model update.

Event Card Anatomy¶

┌──────────────────────────────────────────────────┐
│ [Provider Logo] Provider Name            [Badge] │  ← Header
│ Event Type • Timestamp                           │  ← Metadata
│ ─────────────────────────────────────────────── │
│ Event Title (e.g., "GPT-5 launched")            │  ← Title
│ Event Description (details about the change)     │  ← Description
│ ─────────────────────────────────────────────── │
│ Changes:                                         │  ← Change Details
│ • Price: $10/1M → $8/1M tokens (-20%)           │
│ • Context Window: 128k → 200k tokens            │
│ ─────────────────────────────────────────────── │
│ [View Model Details →]                          │  ← Actions
└──────────────────────────────────────────────────┘

Event Types & Badges¶

Each event type has a color-coded badge:

🔵 Model Discovered — a new model launched
🟢 Pricing Change (green) — price decreased
🟠 Pricing Change (orange) — price increased
🟣 Capability Update — new features added
🔴 Model Deprecated — model being retired
🟡 API Version Change — API breaking changes

Timestamps¶

Timestamps show how long ago an event occurred, for example "2 minutes ago," "3 hours ago," or "2 days ago." Older events show an absolute date instead.

Tip: Events are sorted newest-first, so the most recent event always appears at the top.

Change Details¶

Pricing and capability changes include specific details.

Pricing change example:

Changes:
• Input Price: $3/1M tokens → $2.5/1M tokens (-16.7%)
• Output Price: $15/1M tokens → $12/1M tokens (-20%)
• Context Window: 200k tokens (unchanged)

Capability update example:

Changes:
• Added: Vision (image understanding)
• Added: Function Calling (native tool use)
• Context Window: 128k → 200k tokens

Actions¶

Each event card includes action buttons:

View Model Details →: Opens the full model page with documentation.
See Insights: Opens community tips and best practices, when available.

Community Insights¶

Community Insights are tips, tricks, and best practices shared by Magieva users about specific AI models.

Viewing Insights¶

Click View Model Details on any event card.
Scroll to the Community Insights section.
Browse insights by type:
Best Practices: Recommended usage patterns.
Code Examples: Working code snippets.
Limitations: Known issues and workarounds.
Usage Guides: Step-by-step tutorials.

Insight Card Anatomy¶

┌──────────────────────────────────────────────────┐
│ [Icon] Best Practices                     [Badge]│
│                                                   │
│ Title: "Use Claude 3.5 for code generation"      │
│ Description: "Claude 3.5 Sonnet excels at..."    │
│                                                   │
│ 👍 42 votes   💬 8 comments                      │
│ [View Source →]                                   │
└──────────────────────────────────────────────────┘

Suggesting an Insight¶

Insights are currently read-only. Submitting your own tips, voting, and commenting are not available yet. If you'd like to be notified when submissions open, click Suggest an Insight to join the waitlist.

FAQ¶

General Questions¶

Q: How often does the Discovery Timeline update? A: New models, pricing changes, and capability updates are checked automatically on a regular schedule across all supported providers.

Q: How far back does the timeline go? A: The timeline shows all events collected since Magieva began tracking AI model discovery. Data from before tracking began is not available.

Q: Can I get notifications for specific events? A: Not yet — event notifications aren't currently available.

Q: Is the timeline real-time? A: Events appear shortly after providers announce them, since updates are checked on a regular automated schedule rather than instantly.

Pricing Questions¶

Q: Why do I see a "pricing change" for a model I don't use? A: The Discovery Timeline shows events from all tracked providers, regardless of your current usage. Use the Provider and Event Type filters to narrow the feed to what matters to you.

Q: Are pricing changes retroactive? A: No. Pricing changes shown in the timeline apply to new API calls made after the change date; they don't retroactively affect past usage.

Q: How accurate are the pricing comparisons? A: Pricing data is drawn from provider APIs and public documentation. Actual pricing can vary by region, volume discounts, and enterprise agreements, so always confirm current pricing with the provider directly.

Technical Questions¶

Q: Why do some event cards show "No changes detected"? A: This happens when a new model has been detected but the provider hasn't yet published detailed specifications. The card updates automatically once more information becomes available.

Q: Why does infinite scroll sometimes stop loading more events? A: A few possibilities: 1. You've reached the end of the timeline (no more events to load). 2. There's a network connection issue — check your internet connection. 3. You've made requests very quickly (for example, by rapid scrolling or refreshing) and hit a brief temporary limit — wait a moment and try again. 4. There's a temporary browser issue — try refreshing the page.

Q: Can I export the timeline to CSV or JSON? A: Not currently. You can manually copy event details or take screenshots for now.

Troubleshooting¶

Issue: Page won't load (blank screen)¶

Symptoms: The Discovery page shows a blank screen or a loading spinner that never resolves.

Solutions: 1. Refresh the page (Cmd+R or Ctrl+R). 2. Clear your browser cache and reload. 3. Try a different browser. 4. If the issue persists, contact support@magieva.com.

Issue: Timeline events not displaying¶

Symptoms: The page loads, but shows "No events found" or an empty timeline.

Solutions: 1. Clear all filters and try again. 2. Check back a little later — new events are added on a regular schedule. 3. Try searching for a specific, well-known model (for example, "GPT-4"). 4. If the issue persists, contact support@magieva.com.

Issue: Filters not working¶

Symptoms: Selecting a filter doesn't update the timeline.

Solutions: 1. Refresh the page. 2. Clear your browser cache. 3. Try using a private/incognito browser window. 4. If the issue persists, contact support@magieva.com with details about your browser.

Issue: Infinite scroll not loading more events¶

Symptoms: Scrolling to the bottom of the page doesn't load additional events.

Solutions: 1. Check whether you've simply reached the end of the timeline. 2. Wait a moment — you may have made requests very quickly and hit a brief temporary limit. 3. Refresh the page. 4. Try scrolling more slowly. 5. If the issue persists, contact support@magieva.com.

Issue: "Rate limit exceeded" error¶

Symptoms: A notification appears stating "Rate limit exceeded. Please try again later."

Cause: You've made requests more quickly than allowed in a short time period — usually from rapid scrolling or repeated page refreshes.

Solutions: 1. Wait about a minute before trying again. 2. Scroll more slowly and avoid refreshing the page repeatedly. 3. If you regularly need higher-volume access, contact support@magieva.com.

Providing Feedback¶

We want to hear from you! Your feedback helps us improve the Discovery Timeline.

Email: support@magieva.com with the subject "Discovery Timeline Feedback"

What to include: - What you liked - What confused you - Any bugs you encountered - Features you wish existed

Appendix¶

Supported Providers¶

The Discovery Timeline currently tracks a broad range of AI providers, including:

OpenAI (GPT models, DALL-E, Whisper)
Anthropic (Claude family)
Google (Gemini, PaLM 2)
AWS Bedrock (Titan, Claude, Llama via AWS)
Azure OpenAI Service (GPT models via Azure)
Cohere (Command, Embed)
Mistral AI (Mistral Large, Medium, Small)
AI21 Labs (Jurassic-2)
Replicate (open-source models)
Hugging Face (open-source models)
Stability AI (Stable Diffusion)
Meta (Llama models via Replicate/Hugging Face)
Perplexity AI (pplx models)
Together AI (open-source models)
Fireworks AI (open-source models)

Additional providers are added over time.

Glossary¶

Model: An AI model, such as GPT-4 or Claude 3.5 Sonnet.
Provider: The company offering the AI model, such as OpenAI or Anthropic.
Event: A detected change — a discovery, pricing change, capability update, and so on.
Timeline: A chronological list of events.
Insight: A community-submitted tip, trick, or best practice.

Questions? Contact us at support@magieva.com.