TypingMind

https://developers.googleblog.com/en/gemini-2-5-pro-io-improved-coding-performance/

https://platform.openai.com/docs/models/gpt-image-1

mistral-medium is looking like a very promising contender to GPT4. https://mistral.ai/product/

The paid version of Gemini 2.5 Pro has much higher rate limits than the experimental version. Having access to both would be great.

In Sonnet 3.7, the font size looks too big in the title and subtitle, and content font size is too small

I would like to get response from Claude, Gemini and GPT at the same time and pick the one that best suits my needs in one page. Especially useful for creative tasks - some models are better at some topics than others. Having this options will make TypingMind a way more compelling product for people than going directly to client services.

When I setup a custom model integration via OpenRouter and set this model as default this setting is not persisted and each time I start new chat I need to pick the desired model from the list.

OpenAI launched two new models available with the chat completions API that has web search baked in. gpt-4o-search-preview gpt-4o-mini-search-preview https://platform.openai.com/docs/guides/tools-web-search?api-mode=chat