Models

Choose from various LLM models and manage your model settings

Overview

Highlight allows you to choose from various AI models to suit different tasks:

• Need to analyze large PDF files? Use Gemini Pro

• Looking for fast replies? Try GPT-4o

• The model selection page provides detailed information about each available model

Model Access by Plan

Access to certain models is dependent on your current pricing plan.

Free Plan

Free users get access to Highlight chat with automatically selected models. Highlight will choose the best model for your task to optimize quality and efficiency. You also have access to 200 monthly credits for premium models.

Highlight Pro

With Highlight Pro ($20/month), you get:

• Access to flagship premium models including Claude 4.5 Sonnet, GPT-5 Max, and Gemini 2.5 Pro

• 2,000 credits per month for premium model usage

• The ability to manually select your preferred model for each conversation

• Bring Your Own Key (BYOK) functionality - use your own API keys without using your Highlight credits

Setting Your Default Model

Users can set a model as their "daily driver" for regular use. This model will be used by default for your conversations, but you can easily switch to other models on the fly using the mentions menu.

Bring Your Own Key (BYOK) (Pro Only)

Pro subscribers can bring their own API keys from providers like OpenAI, Anthropic, or Google. When you use your own keys:

• You won't be charged Highlight credits for those model interactions

• You'll pay the provider's public API costs directly

• You still need an active Pro subscription to use this feature

• Navigate to the model settings page to add your API keys for different providers

Adding Custom Models

For those wanting to test brand new models, Highlight Pro allows you to add custom models with your preferred provider:

1. Select a provider (e.g., OpenAI) from the dropdown (You can also set Base URL by selecting Custom provider)

2. Enter the model name (e.g., gpt-4o)

3. Add your API key

4. Complete optional fields like display name and description

5. Click "Add Provider"

Model Capabilities

When adding a custom model, selecting the correct capabilities is essential for proper functionality:

• Streaming: Enables real-time responses as they're generated

• Function Calling: Allows the model to use tools and functions

• Parallel Function Calling: Supports calling multiple functions simultaneously

• Response Schema: Supports structured outputs in specific formats

• Vision: Enables the model to process and understand images

• Prompt Caching: Stores prompts for improved performance

• System Message: Supports system-level instructions

• Developer Message: Supports developer-specific instructions

• Tool Choice: Allows the model to select appropriate tools

• Thinking: Supports extended reasoning capabilities

• Temperature: Allows adjusting randomness in model responses

Pricing Tier List

Higher tiers correspond to an increased cost per token.

FAQ