> ## Documentation Index
> Fetch the complete documentation index at: https://camelai.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Model Selection Guide
> Learn how to choose the right AI model for your camelAI iframe implementation
**camelAI Legacy Product** — This documentation covers camelAI's embedded analytics offering, which is no longer being actively developed. We are migrating existing customers to the new camelAI platform. For the current product, visit [camelAI](https://camelai.dev).
Selecting the appropriate model is crucial for optimizing your users' experience with camelAI. Different models offer unique strengths in terms of intelligence, speed, cost, and interaction style. This guide will help you choose the model that best fits your use case.
## How Model Selection Works
When you create an iframe through the camelAI API, you specify which model to use. This model choice is locked for that specific chat conversation - ensuring consistency throughout the user's interaction. If users access previous conversations, camelAI automatically uses the model that was originally selected for that chat.
## Available Models
We currently support five models across two providers:
### Model Comparison
| Model | Provider | Best For | Speed | Cost | Intelligence |
| ------------------- | --------- | ------------------------------------------------- | --------- | ------- | ------------ |
| **GPT-5** (Default) | OpenAI | Complex multi-step workflows, long-context | Medium | Medium | Very High |
| **O3** | OpenAI | Complex queries, tool-heavy workflows | Medium | Highest | Very High |
| **Sonnet 4.0** | Anthropic | In-depth research, comprehensive analysis | Medium | Highest | Very High |
| **O4 Mini** | OpenAI | Simple data, cost-conscious deployments | Fast | Low | High |
| **4.1** | OpenAI | Speed-critical applications, straightforward data | Very Fast | Lowest | Medium |
## Model Characteristics
Our recommended default model offering state-of-the-art reasoning and reliability.
**Strengths:**
* Strong long-context understanding
* Excellent multi-turn coherence and instruction following
**Considerations:**
* Typically slower than lightweight models for simple tasks
**Use GPT-5 when:**
* Your data requires complex joins or calculations
* Accuracy is more important than speed
A strong general-purpose model that balances capability and cost for many use cases.
**Strengths:**
* Excellent at complex reasoning and tool calling
* Provides concise, focused responses
**Considerations:**
* Higher cost than O4 Mini and GPT-5
* Medium response times
**Use O3 when:**
* Your data requires complex joins or calculations
* Accuracy is more important than speed
An exceptionally capable model that excels at thorough analysis.
**Strengths:**
* Extremely helpful and proactive
* Excellent for exploratory data analysis
**Considerations:**
* Provides more information than requested
* Slower response times
**Use Claude Sonnet 4.0 when:**
* Users perform in-depth research or exploration
* User questions tend to be open-ended
A cost-effective model that handles straightforward queries well.
**Strengths:**
* Significantly lower cost than O3
* Faster response times
* Clear, direct communication style
**Considerations:**
* Less capable with complex reasoning
* May struggle with nuanced queries
**Use O4 Mini when:**
* Your data schema is simple and well-structured
* Most queries are straightforward lookups
* Cost optimization is a priority
The fastest model in our lineup, optimized for speed.
**Strengths:**
* Fastest response times by far
* Efficient for simple tasks
**Considerations:**
* Limited reasoning capabilities
* Best suited for basic queries only
* More expensive per token, but generates less tokens so typically cheaper overall
**Use 4.1 when:**
* Speed is the absolute priority
* User queries are simple and predictable
## Best Practices
### Test Before Production
We strongly recommend experimenting with different models using your actual data before deploying to production. Model performance can vary significantly based on:
* Your data structure complexity
* Typical query patterns
* User expectations
* Performance requirements
## Updates and Support
We continuously evaluate and update our model offerings to provide the best possible experience. This guide will be updated as new models become available or existing models are improved.
If you don't see a model that meets your requirements, we'd love to hear from you. Contact us to request additional model support.