Image Generation
Steinkauz supports image generation as a tool inside chat. When the tool is enabled, the model can create images from your description (e.g. “a sunset over the ocean”) using supported providers such as OpenAI DALL·E and Black Forest Labs.
How it works
- You chat as usual; when the model decides an image is needed, it calls the image-generation tool.
- The tool uses the image provider(s) available on your plan (Gateway or BYOK). The exact provider depends on your model and provider configuration or BYOK setup.
- The generated image is shown in the conversation.
Enabling image generation
Image generation is typically toggled per conversation or in the chat/tools settings. If it is enabled and your selected model supports it, the model can use it when appropriate.
Provider and cost notes
- Gateway: Image generation uses your plan’s inference budget and the providers allowed by your Gateway provider configuration.
- BYOK: Image generation uses your configured providers and their pricing. Ensure you have an image-capable provider set up in BYOK Provider Configuration.
Usage appears in Usage statistics and cost breakdown.
Last updated on