FEAT: Improve models and usage documentation

Adds a new section explaining model choices and usage limits, as well as providing tips for optimizing usage. Also includes screenshots for subscription options and top-up credits.

docs/models-and-usage.mdx

@@ -0,0 +1,74 @@
+---
+title: 🚀 Models & Usage
+description: PearAI Tips for Models & Usage
+keywords: [pearai, models, usage, tips, recommendations]
+---
+
+## 🧠 Models
+
+Current Models included with the Junior Engineer plan are *Claude 3.5 Sonnet*, *Open AI GPT-4o* and *Claude 3 Haiku*.
+ The 10X Engineer plan comes with the same models as the Junior Engineer plan, plus *GPT-o1-preview* and *GPT-o1-mini*.
+
+Pear AI is designed to give you a flexible and a powerful AI experience. You can choose to bring your own API keys or use local models. You can choose the model or host that best suits your needs! We offer a wide range of options, including:
+
+<div style={{ display: 'flex', flexWrap: 'wrap', padding: '10px' }}>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>Anthropic</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>Groq</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>OpenAI</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>DeepSeek</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>Azure OpenAI</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>TogetherAI</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>Mistral</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>Google Gemini</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>Ollama</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>LM Studio</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>Cohere</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>Llamafile</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>WatsonX</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>Replicate</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>OpenRouter</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>Llama.cpp</div>
+  <div style={{ flex: '1 1 45%', boxSizing: 'border-box', margin: '5px', minWidth: '200px' }}>Other OpenAI Compatible APIs</div>
+</div>
+<br />
+
+# 🔧 Usage
+
+## Subscriptions
+
+To ensure everyone enjoys a smooth and equitable experience, we've implemented a usage system.
+
+When you sign up for a PearAI Junior Engineer or a 10X Engineer Plan, you get a set monthly allowance of credits. Your PearAI usage depends on your prompt input and output sizes.  On average, this equates to around 700 requests.
+
+*An explanation of how credits are used, how many you get, and how that compares to token usage, will be coming soon.*
+
+![alt text](/img/subscribe.png)
+
+## Top Up!
+
+If you run out of monthly credits, don't worry; *you can get more credits with our Top Up plans!*
+
+![alt text](/img/top-up.png)
+
+*Right now, while PearAI is in Beta, if you run out of credits you can email [PearAI Support](mailto:[email protected]) and we will top you off!*
+
+## What are the usage limits?
+
+Pear AI's usage is measured in "messages." Every interaction counts, whether you're sending a message, uploading a file, or receiving a response from your chosen AI model.
+
+Keep in mind that longer messages and larger files use up more of your limit. Similarly, long conversations with lots of back-and-forth will consume your limit faster.
+
+At this time, when you pay for an early bird pro subscription, there are no hard usage limits and the our team will top you off if you run out of credits. However, to cut down on costs so we can continue to provide you with the best AI experience, it is best to maximize your prompts and context to reduce the number of messages you send.
+
+## How can I maximize my Pear AI usage?
+
+Here are a few tips to help you get the most out of Pear AI:
+
+- **Start new conversations**: When you switch to a new topic or have unrelated questions, start a fresh conversation. This helps keep your conversations manageable and optimizes your usage.
+- **Bundle your questions**: Instead of sending one question at a time, try asking multiple questions at once. This is a more efficient way to get the information you need.
+- **Avoid re-uploads**: Once you've uploaded a file, you don't need to upload it again in the same conversation. Pear AI remembers the information from your earlier uploads.
+- **Provide relevant context**: While Pear AI can access your entire codebase, you'll get the best results by specifically including only the files that are directly related to your request. This helps Pear AI focus on the most pertinent information and provide more accurate and helpful responses.
+
+:::info
+We understand that usage limits can sometimes be a bit confusing. We're always striving to improve Pear AI and provide the best possible AI experience. If you have any questions or concerns, please don't hesitate to contact us by [email](mailto:[email protected]) or join our [Discord](https://discord.gg/7QMraJUsQt).
+:::