> ## Documentation Index
> Fetch the complete documentation index at: https://watermelon.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Choose your AI model
> There are different AI models available for your Agent. Which model is the best choice, depends on the use case of your Agent. This article will help you choose the best model for your Agent.
## What are AI Models?
AI models are the engine behind your AI Agent. They process input (like customer questions) and generate output (like answers). Each model has unique strengths in reasoning, speed, memory, and language capabilities. Understanding these differences helps you build a more effective AI Agent.
## How to choose the best model for your Agent?
Is it answering FAQs, guiding users through tasks, or automating actions?
What is the most important thing the Agent should do?
* **Speed:** Do you want fast replies, or can the Agent take some more time?
* **Length of answers:** Does the Agent need to give long answers, or quick and short?
* **Sources:** How many sources does the Agent need for answering questions?
Use the table below to find the best model for your situation:
| Use case | Examples | Recommended model | Guidance |
| :--------------------------------------- | :-------------------------------------------------------------------------------------------------------------------- | :---------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Basic conversations | FAQ questions, delivery status checks, booking confirmations | **GPT 5.4 Nano** | Use for simple, high-volume conversations where speed matters most. This is the fastest AI Engine 2.0 model and is ideal for repetitive questions that can be answered from clear knowledge base content. |
| Longer or more complex customer journeys | Insurance claims, onboarding processes, resolving complex questions across multiple messages | **GPT 5.4 Mini** | Use for customer journeys that require more context, better interpretation, and higher answer accuracy across multiple messages. |
| Smart, complex conversations | Troubleshooting, legal compliance, internal IT policies, complex customer support | **GPT 5.4 Mini** | Use when reliability and reasoning are more important than maximum speed. Recommended for conversations where the Agent needs to combine multiple sources or handle nuanced questions. |
| Internal Support Agents | HR, IT, and finance questions, leave requests, password resets, payroll explanations | **GPT 5.4 Mini** | Use for internal support where policy accuracy and clear explanations matter. For very simple, high-volume internal FAQs, **GPT 5.4 Nano** can also be used. |
| Multilingual support | Agents that switch smoothly between Dutch, English, German, French, Spanish, or other languages | **GPT 5.4 Mini** | Use for multilingual organizations where answer quality and reliable retrieval across languages are important. AI Engine 2.0 is designed to find the right knowledge more consistently, even when the question and knowledge base are in different languages. |
| Agent needs to know date and time | Reservations, new launches, pricing changes, policy updates, availability questions | **GPT 5.4 Mini** | Use when the Agent needs to interpret time-sensitive information carefully. Make sure the relevant website, knowledge base, documentation, or product feed has been re-crawled so the Agent uses the latest available knowledge. |
| Agent needs to execute Actions | Triggering workflows, creating CRM entries, booking meetings, checking order status, performing multistep automations | **GPT 5.4 Mini** | Use for Agents that work with Actions or integrations. AI Engine 2.0 supports more dynamic tool choice, allowing the Agent to select the most relevant action based on the customer’s request. Add clear instructions that define when the Agent is allowed to trigger actions and when it should ask for confirmation. |
| Large product catalogs | Webshops with many similar products, product comparisons, product availability questions | **GPT 5.4 Mini** | Use when the Agent needs to distinguish between similar products, product names, variants, or specifications. AI Engine 2.0 improves entity recognition, helping the Agent understand exactly which product the customer means. |
| Many SKUs or technical identifiers | SKU comparisons, order numbers, product codes, locations, company names, technical references | **GPT 5.4 Mini** | Use when precision is important. AI Engine 2.0 recognizes specific entities such as SKUs, product names, order numbers, company names, locations, and function names, which reduces confusion and improves answer accuracy. |
| High-volume automation | First-line customer support, ecommerce support, repetitive support questions | **GPT 5.4 Nano** | Use when the goal is to automate a large number of straightforward conversations as quickly as possible. Nano is the best fit when speed and scalability are the main priorities. |
| Accuracy-critical support | Compliance-sensitive questions, technical documentation, API documentation, policy explanations | **GPT 5.4 Mini** | Use when incorrect answers create higher risk. Mini benefits most from AI Engine 2.0 improvements such as Hybrid Search, reranking, improved RAG, better source selection, and smarter follow-up questions. |
**Model recommendation note**
AI Engine 2.0 introduces **GPT 5.4 Nano** and **GPT 5.4 Mini** as the recommended models. Other models may still be available in the platform, but for new and upgraded Agents, customers should be guided toward these two models because they are optimized for AI Engine 2.0.
Use **GPT 5.4 Nano** when speed, scale, and simple automation are the main priorities.
Use **GPT 5.4 Mini** for most other use cases, especially when conversations are more complex, the knowledge base is larger, accuracy matters more, or the Agent needs to use Actions.
If you choose **GPT-5** as your model, it’s essential to include an instruction in your Agent’s setup that clearly states it is **not allowed to independently execute tasks or take actions**.\
\
GPT-5 has advanced reasoning and autonomy, so without this kind of instruction, it may try to take initiative where it shouldn’t.
Example instruction: *“You are not allowed to take actions, complete tasks, or trigger workflows.”*
## **Missing your use case in the above schedule?**
Compare the different models below to find the best match. The questions below can help you.
* **Do you need fast responses?** Go for a mini or nano version of your preferred model
* **Do you want the Agent to be able to handle a lot of information?** Use a model with a high context window.
* **Do you want the Agent to provide detailed answers?** Go for a model with high output tokens.
* **Do you want the Agent to think well, make connections, and solve complex tasks?** Go for an Agent with high reasoning.
| Model | Reasoning | Speed | Input | Output | Context Window | Max Output Tokens | Knowledge Cutoff |
| :--------------- | :-------- | :------ | :---------- | :----- | :------------- | :---------------- | :--------------- |
| **GPT-5.4-mini** | Higher | Fast | Text, Image | Text | 400,000 | 128,000 | Aug 31, 2025 |
| **GPT-5.4-nano** | High | Fast | Text, Image | Text | 400,000 | 128,000 | Aug 31, 2025 |
| GPT-5.1 | Highest | Medium | Text, Image | Text | 500,000 | 200,000 | Dec 01, 2024 |
| GPT-5 | Higher | Medium | Text, Image | Text | 400,000 | 128,000 | Oct 01, 2024 |
| GPT-5-mini | High | Fast | Text, Image | Text | 400,000 | 128,000 | May 31, 2024 |
| GPT-4.1 | Higher | Medium | Text, Image | Text | 1,047,576 | 128,000 | Jun 01, 2024 |
| GPT-4.1-mini | High | Fast | Text, Image | Text | 1,047,576 | 32,768 | Jun 01, 2024 |
| GPT-4o | High | Medium | Text, Image | Text | 128,000 | 16,384 | Oct 01, 2023 |
| o3 | Highest | Slowest | Text, Image | Text | 200,000 | 100,000 | Jun 01, 2024 |
| o3-mini | Higher | Medium | Text | Text | 200,000 | 100,000 | Oct 01, 2023 |
You can always test different models and compare them using the Playground.