# Capabilities

- [Completion and Chat Completion](https://docs.aimlapi.com/capabilities/completion-or-chat-models.md): An explanation of completion and chat completion terms.
- [Streaming Mode](https://docs.aimlapi.com/capabilities/streaming-mode.md)
- [Code Generation](https://docs.aimlapi.com/capabilities/code-generation.md): Description of code generation as a capability of some our AI models and a list of supporting models.
- [Function Calling](https://docs.aimlapi.com/capabilities/function-calling.md): Learn how to connect large language models to external tools using function calls.
- [Thinking / Reasoning](https://docs.aimlapi.com/capabilities/thinking-reasoning.md)
- [Vision in Text Models](https://docs.aimlapi.com/capabilities/image-to-text-vision.md)
- [Web Search](https://docs.aimlapi.com/capabilities/web-search.md)
- [Batch Processing](https://docs.aimlapi.com/capabilities/batch-processing.md)
- [Model comparison](https://docs.aimlapi.com/capabilities/models-comparsion.md): A practical example for comparing responses from different models to the same question.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.aimlapi.com/capabilities.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.