AI Models Guide
Choose the right model for every task
Lookinglass gives you access to 21 OpenAI models across two families: 14 Chat models for fast, versatile conversations and 7 O-series models for complex reasoning tasks. This guide helps you choose the right model and settings for your needs.
Understanding the Basics
Tokens & Pricing
Tokens are how AI models measure text. Roughly 1 token ≈ 4 characters, so "Hello world!" is about 3 tokens. Both your messages and the AI's responses are measured in tokens.
- 100 tokens ≈ 75 words (one paragraph)
- 1,000 tokens ≈ 750 words (one page)
Every model has a rate per million tokens. Your cost is simple: tokens used × model rate. Lookinglass shows you the maximum possible cost before you send each message—no surprises, ever.
AI Workspace
Your AI's workspace is its total "working memory"—the maximum amount of information it can process in a single request. Think of it as the AI's desk space that must accommodate everything it needs to work with.
- Your current message what you're asking
- Context window recent conversation history
- Permanent memory your preferences and style
- Its response the answer it generates
- Internal reasoning for reasoning models
Bigger context = more conversation history the AI remembers.
Chat Models (14 Available)
General-purpose conversation and task completion models, perfect for everyday AI interactions.
gpt-5 Series (5 Models)
Latest generation models with newest knowledge (Sep 2024) and enhanced reasoning capabilities. Learn more from OpenAI.
| Model: | gpt-5-pro | gpt-5 | gpt-5-chat-latest | gpt-5-mini | gpt-5-nano |
| Reasoning: | ●●●●● | ●●●●○ | ●●●○○ | ●●●○○ | ●●○○○ |
| Speed: | ⚡○○○○ | ⚡⚡⚡○○ | ⚡⚡⚡○○ | ⚡⚡⚡⚡○ | ⚡⚡⚡⚡⚡ |
- models: gpt-5, gpt-5-pro, gpt-5-chat-latest, gpt-5-mini, gpt-5-nano
- best for: complex reasoning, creative writing, advanced problem solving
- context: 400K tokens (gpt-5-chat-latest: 128K)
- smart savings: gpt-5, gpt-5-mini, gpt-5-nano (50% off)
- starting from: $0.00001 per message
gpt-4o Series (3 Models)
High-performance models optimized for speed and efficiency while maintaining quality. Technical deep dive (system card).
| Model: | chatgpt-4o-latest | gpt-4o | gpt-4o-mini |
| Intelligence: | ●●●○○ | ●●●○○ | ●●○○○ |
| Speed: | ⚡⚡⚡○○ | ⚡⚡⚡○○ | ⚡⚡⚡⚡○ |
- models: chatgpt-4o-latest, gpt-4o, gpt-4o-mini
- best for: general tasks, analysis, coding assistance
- context: 128K tokens
- smart savings: no
- starting from: $0.00003 per message
gpt-4.1 Series (3 Models)
Smartest non-reasoning models with massive 1M token context window—highest intelligence rating for non-reasoning models from OpenAI.
| Model: | gpt-4.1 | gpt-4.1-mini | gpt-4.1-nano |
| Intelligence: | ●●●●○ | ●●●○○ | ●●○○○ |
| Speed: | ⚡⚡⚡○○ | ⚡⚡⚡⚡○ | ⚡⚡⚡⚡⚡ |
- models: gpt-4.1, gpt-4.1-mini, gpt-4.1-nano
- best for: highest quality output, long documents, complex analysis
- context: 1M tokens
- smart savings: no
- starting from: $0.00002 per message
gpt-4 Legacy (2 Models)
Original gpt-4 models, still powerful for many applications.
| Model: | gpt-4 & gpt-4-turbo |
| Intelligence: | ●●○○○ |
| Speed: | ⚡⚡⚡○○ |
- models: gpt-4 (8K), gpt-4-turbo (128K)
- best for: established workflows, compatibility needs
- context: 8K - 128K tokens
- smart savings: no
- starting from: $0.001 per message
gpt-3.5 Series (1 Model)
Cost-effective model perfect for high-volume, straightforward tasks.
| Model: | gpt-3.5-turbo |
| Intelligence: | ●○○○○ |
| Speed: | ⚡⚡○○○ |
- models: gpt-3.5-turbo
- best for: simple questions, basic tasks, cost optimization
- context: 16K tokens
- smart savings: no
- starting from: $0.00007 per message
O-Series Reasoning Models (7 Available)
Advanced reasoning models that "think" step-by-step through complex problems, perfect for mathematics, logic, and detailed analysis.
o3 Series (3 Models)
Latest generation reasoning models with configurable thinking depth for complex problems. Learn more from OpenAI.
| Model: | o3-pro | o3 | o3-mini |
| Reasoning: | ●●●●● | ●●●●● | ●●●●○ |
| Speed: | ⚡○○○○ | ⚡○○○○ | ⚡⚡⚡○○ |
- models: o3, o3-pro, o3-mini
- best for: complex reasoning, research-level problems, mathematical proofs
- AI power levels: light, standard, power, ultimate (affects cost and thinking time)
- context: 200K tokens
- smart savings: o3, o3-mini (50% off)
- starting from: $0.003 per message
o1 Series (3 Models)
First-generation reasoning models that pioneered step-by-step thinking for complex problems. Learn more from OpenAI.
| Model: | o1-pro | o1 | o1-mini |
| Reasoning: | ●●●●○ | ●●●●○ | ●●●○○ |
| Speed: | ⚡○○○○ | ⚡○○○○ | ⚡⚡○○○ |
- models: o1 (200K), o1-pro (200K), o1-mini (128K)
- best for: mathematical problems, logical reasoning, academic work
- AI power levels: fixed (no configuration)
- context: 128K - 200K tokens
- smart savings: no
- starting from: $0.004 per message
o4-mini
Efficient reasoning model designed for everyday logical tasks without the cost of larger models. Learn more from OpenAI.
| Model: | o4-mini |
| Reasoning: | ●●●●○ |
| Speed: | ⚡⚡⚡○○ |
- models: o4-mini (1 model)
- best for: basic reasoning, educational problems, logic puzzles
- AI power levels: light, standard, power, ultimate
- context: 200K tokens
- smart savings: yes (50% off)
- starting from: $0.002 per message
Choosing the Right Model
Fastest & Cheapest
Quick answers, simple tasks, basic questions
- recommended: gpt-4.1-nano
- why: lightning fast, lowest cost
- example: "What's the capital of France?" or "Fix this syntax error"
Best Overall (Default)
Most chats, summaries, balanced speed and cost
- recommended: gpt-4.1-mini
- why: 1M token window, fast, affordable
- example: "Summarize this article" or "Help me write an email"
Highest Quality
Advanced work, creative projects, complex conversations
- recommended: gpt-4.1, gpt-5-chat-latest, or gpt-4o
- why: gpt-4.1 (highest intelligence + 1M context), gpt-5-chat-latest (latest knowledge), gpt-4o (proven)
- example: "Write a detailed business plan" or "Refactor this codebase"
Fastest & Cheapest Reasoning
Quick step-by-step thinking on a budget
- recommended: gpt-5-nano
- why: cheapest reasoning model available
- example: "Explain this concept step-by-step"
Balanced Reasoning
Solid reasoning for everyday problems
- recommended: gpt-5-mini
- why: balanced speed, cost, and reasoning quality
- example: "Walk me through solving this problem"
Advanced Reasoning
Complex math, logic, research-level problems
- recommended: o3 (smart savings)
- why: best reasoning outside pro models, 50% off
- example: "Solve this calculus problem" or "Debug this algorithm"
Advanced Settings
Creativity Level
Controls how creative or focused the AI's responses are.
- low (0.2): focused, consistent, factual responses
- balanced (1.0): balanced creativity and accuracy (default)
- high (1.5): creative, varied, sometimes unexpected
AI Power Level (Reasoning Models)
How much time the AI spends thinking through problems.
- light: minimal thinking, fastest, lowest cost (gpt-5 family only)
- standard: quick thinking, good for most tasks
- power: deeper thinking, balanced cost and quality
- ultimate: maximum thinking, highest cost, best quality
Response Detail Level (Select gpt-5 Models)
Controls how much detail the AI includes in its responses.
- concise: brief, to-the-point answers
- balanced: standard level of detail (default)
- detailed: thorough, comprehensive explanations
Billing Plan
Choose between speed and savings based on your needs.
fast & reliable: instant responses, standard pricing
smart savings: 50% off, slight delay (select models only)- availability: gpt-5, gpt-5-mini, gpt-5-nano, o3, o3-mini, and o4-mini