Releasesby IbisRetool-provided AI models on the Business plan
UpdateyesterdayUnverifiedAdded Oct 14, 2026
Live on cloud Organizations on the Business plan now have access to Retool-provided AI models for app building. These models, prefixed with Retool , have been tuned by Retool for enhanced performance and speed for app building. The following Retool-provided models are supported: Retool Mini Retool Power
Topics: Pricing, Performance
More Retool releases
Every Retool releaseSelf-hosted Retool 4.34 and 4.0 stable updates
The following patches are now available on the Stable release channel: Retool 4.34.8 Retool 4.0.21 Update your Retool instance to apply the latest bug fixes and security patches.
Self-hosted Retool 4.34 stable updates
The following patches are now available on the Stable release channel: Retool 4.34.7 Update your Retool instance to apply the latest bug fixes and security patches.
Retool 4.70 Edge for self-hosted instances
Retool 4.70 is now available on the Edge release channel for self-hosted organizations.
Custom authentication for embedded apps
Live on cloud • Business • Enterprise Business and Enterprise organizations can now use the Retool API to authenticate apps that are embedded in an app or website external to Retool. Once configured, the custom authentication flow exchanges an API token for an embed URL.
New OpenAI models available in Retool
Live on cloud Retool now supports the following new AI models for AI resource queries : GPT 6 Luna . GPT 6 Sol . Enterprise only: GPT Image 2.5 Flare . Must bring your own key. Enterprise only: GPT Image 2.5 Sunburst . Must bring your own key.
Create PostgreSQL and REST API resources with natural language
Live on cloud • All plans Public beta You can now prompt the app building agent to create REST API or PostgreSQL resources directly from the app builder. Describe the resource that you want to create, and the agent initiates the resource creation process. You'll be asked to provide credentials or more details where applicable.
Self-hosted Retool 4.34, 4.0, and 3.334 stable updates
The following patches are now available on the Stable release channel: Retool 4.34.6 Retool 4.0.19 Retool 3.334.31 Update your Retool instance to apply the latest bug fixes and security patches.
Retool-provided AI models on the Team plan
Live on cloud Organizations on the Team plan can now use Retool-provided AI models for app building, in addition to the full catalog of supported models. These models, prefixed with Retool , have been tuned by Retool for enhanced performance and speed for app building.
Also shipped on Oct 13, 2026
Retool in October 2026What's included:
- Three training methods: Supervised fine-tuning (SFT) , direct preference optimization (DPO) , and reinforcement learning with group relative policy optimization (GRPO) . Each method trains a low-rank adapter (LoRA) or the full model weights. Custom loss functions : Train with any objective you compute in PyTorch from the model's log-probabilities.
The AI.AGG function is generally available (GA)
The AI.AGG function is generally available (GA). You can use this function to semantically aggregate unstructured input data based on natural language instructions.
BigQuery generative AI functions now support the gemini-4-argon model
BigQuery generative AI functions now support the gemini-4-argon model. This model is generally available .
Gemini 4 Argon in CodeMender (Preview)
CodeMender now supports Gemini 4 Argon. To use it, pass --model gemini-4-argon to cm find , cm verify , or cm fix . Gemini 3.8 Flash remains the default model. For more information, see Specifying the model .
Gemini 4 Argon and Gemini 4 Argon Cyber Permissive
Gemini 4 Argon ( gemini-4-argon ) is available in General Availability (GA) . Gemini 4 Argon is Google's frontier model that excels at deep work in complex, real-world tasks across domains including coding, finance, legal, cybersecurity, and science.
On-demand state repartitioning is now generally available
On-demand state repartitioning is now generally available. You can resize the number of shuffle partitions for a stateful Structured Streaming query or Lakeflow pipeline without losing checkpoint state. See On-demand state repartitioning for stateful streaming queries .