feat: add GPT-4.1 nano model support

[gabriel-ecegi]

• What kind of change does this PR introduce?
  Feature - Add support for GPT-4.1 nano model

• What is the current behavior?
  The codebase currently supports GPT-4.1 and GPT-4.1 mini models, but does not include the GPT-4.1 nano model which is the fastest and most cost-efficient version of
  GPT-4.1.

• What is the new behavior (if this is a feature change)?
  This PR adds full support for the GPT-4.1 nano model (gpt-4.1-nano) across both Chat Completions and Responses APIs with:

• Model enum definition in AxAIOpenAIModel and AxAIOpenAIResponsesModel

• Pricing configuration: $0.10 per 1M input tokens, $0.40 per 1M output tokens

• 1,047,576 token context window

• 32,768 max output tokens

• Support for text and image input, streaming, function calling, structured outputs, and predicted outputs

The model is positioned after GPT-4.1 mini in the model hierarchy, following the pattern: GPT-4.1 → GPT-4.1 mini → GPT-4.1 nano

• Other information:
  Pricing and specifications are based on the official OpenAI documentation for GPT-4.1 nano. This model is ideal for high-volume, latency-sensitive applications that
  require fast inference at minimal cost.