We’re excited to introduce Multi-provider support, aka BYOK (Bring Your Own Keys), a new major feature that enables you to use personal API keys for a pay-as-you-go license and choose from multiple AI providers for more flexibility. This update also brings a one-time purchase licensing option, enhanced provider modes, and improved user experience.

Release Summary

🤖 Choose your AI engine
Use xAI, Google AI, OpenAI, Anthropic, DeepSeek, OpenRouter, Ollama, or any OpenAI-spec compliant provider – mix and match them to suit each task.

💡 Run models locally with Ollama
Keep your prompts private and offline by running local models right on your machine.

🔑 Pay-as-you-go with your own API keys
Got an OpenAI key? Add it to TextWisely and use a one-time purchase license without a subscription.

⚡ Fresh models for subscribers

• Fast: Gemini 2.5 Flash-powered

• Balanced: GPT-4.1 Mini-powered

🗣️ Per-action provider control
Assign specific models to certain actions, or set a default for deeper reasoning tasks.

With this update, you decide how to balance speed, privacy, cost, and capability.

New Features

• BYOK (Bring Your Own Keys) functionality with multi-provider support, enabling the use of personal API keys (e.g., OpenAI)

  • xAI, Google AI, OpenAI, Anthropic, DeepSeek, OpenRouter, Ollama, and any custom OpenAI spec-compliant provider are supported

  • Tip: In cases where you need to ensure data does not leave your machine, Ollama integration can be used with local models

• Support for one-time license purchases with pay-as-you-go pricing (BYOK)

• New models for the TextWisely provider (available with a subscription license):

  • Fast: Gemini 2.5 Flash-based

  • Balanced: GPT 4.1 Mini-based

• You can assign different providers (models) to specific actions or set a default provider

Improvements

• Added helpful messages to inputs in settings

• Updated help link within the onboarding

Fixes

• Fixed an issue where tags in user messages, e.g., {{SOMETHING}}, were removed from the response