TypingMind

Although not available in normal Gemini app. Gemini Flash 2.5 has option to turn of reasoning entirely (in aiStudio). Knowing that aiStudio is essentially using the API backend, we know for sure this can be turned on and off for API. In TypingMind, for Gemini 2.5 Flash API, there are only options for (low/medium/high). No option to turn that off completely. This is important to us because (1) It is my most favorite model. (2) There is no option for us in normal Gemini App. (3) It's fast. lets make it fastest. (4) I hate reasoning models. Please make our dreams come true.

Support the new features assuming the API key is from a verified organization

Right now, the only way to use custom system instructions is by setting up a custom agent. The problem is, once you use a custom agent, you're locked into the agent’s parameters like temperature, max tokens, etc. and can't dynamically switch models or modify those parameters mid-conversation. What’s missing is the ability to define system instructions on a per-model level, not just per-agent. I don’t use the same system message for GPT-4.1 as I do for claude 3.7 Having one static system prompt doesn’t reflect how these models are used differently. By allowing custom system instructions tied to each model (independent of the agent setup), we could use dynamic parameters during a conversation without being blocked by agent-level defaults.

I saw on the OpenAi page that o1-pro is avaliable via api endpoint. When will you add it?

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 OpenRouter API keys to have the same extended functionality as TypingMind supports for OpenAI/Antropic/Gemini: Ability to secure with master password Ability to assign different keys to different profiles Ability to sync model and key separately

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.

With these TTS models that are only available via API, it would be great to access them through Typing Mind to create audiobooks or other long-form audio content (to download large MP3/WAV files).

When switching from a Vision-enabled Agent (like GPT-40) to a non-Vision-enabled model (like O3 Mini), an error occurs: “Sorry, OpenAI has rejected your request. Here is the error message from OpenAI: Invalid content type. image_url is only supported by certain models.” Scenario: I use GPT-40 with Vision Support to handle images and convert attachments to text successfully. When switching back to O3 Mini, it tries to process the image and fails with the above error. Expected Behavior: Images should be excluded from being sent to models that do not support them. This would prevent errors and ensure smoother transitions between models. Current Workaround: Deleting all image-related messages before resuming with a non-Vision model. Proposed Solution: Introduce logic to exclude image data when interacting with models that don't support vision capabilities.

Failed to pass the test when adding the qwq-plus-latest model on the Aliyun platform. This model only supports streaming transmission, while the test button for adding the model uses non-streaming transmission, which causes the addition to fail. Please make improvements.