Google just released Gemini 2.5 Pro to Preview This includes releasing the API pricing and higher rate limits for paid users. However, looks like the higher rate limit is only available for Tier 3 users, which requires spending at least $1,000 on Gemini Pricing: Input (per 1M tokens): - $1.25, prompts <= 200k tokens - $2.50, prompts > 200k tokens Output (per 1M tokens): - $10.00, prompts <= 200k tokens - $15.00, prompts > 200k Grounding with Google Search costs $35 / 1,000 requests The experimental model is still available and free to use. Overall, the pricing is in line with the other models. The pricing is almost identical to Claude 3.7 Sonnet for prompts with over 200k tokens, and it is 50% off for shorter requests. Read more about the pricing here: https://ai.google.dev/gemini-api/docs/pricing Check out the model here: https://deepmind.google/technologies/gemini/pro/

There are a few ways to run a LLM locally. One of the more straightforward is to use ollama. This video will explain the basics. If you want some help getting going leave a comment.

The team that brought you Pydantic has built a framework for creating AI agents. This video will get you started. Note: This video is the first in a series. If you want me to add that as a course in our community to help you keep track let me know if the comments.

I have implemented icon generation using DALL-E 3; however, it cannot handle transparency for background. Fortunately, I discovered this library to remove background and make it transparent. Hopefully, it can help solve some of your issues: https://github.com/imgly/background-removal-js