Build reusable AI workflows from image generation to editing and scale

Frequently asked questions

What images is InkRoom best suited to generate?

Image generation and editing are InkRoom's primary business. It supports posters, ecommerce listings, product detail pages, design images, comics, portraits and marketing images, including prompt- or reference-based edits.

Can I try InkRoom image generation for free?

Eligible guests can try text-to-image for free. Remaining uses and models are shown before prompt entry; availability, daily limits and models follow live configuration, and only successful images use the allowance. Reference-image editing requires sign-in and follows account access and live pricing.

Does InkRoom support GPT Image 2 and gemini-3.8-flash?

Use channels enabled and marked image-capable in the current environment. Callable IDs such as gpt-image-2 and gemini-3.8-flash, capabilities and pricing come from the live catalog; an absent channel is not advertised as available. Channel IDs do not automatically equal an official image-model name.

Do the API and MCP support concurrent image generation?

Yes. Website, API and MCP use separate concurrency pools by default. The actual limit is determined by account entitlements, and administrators can switch an individual user to one shared pool.

How do I access image models through the API?

InkRoom provides an OpenAI-compatible /v1 API and a Gemini-compatible /v1beta API, so configured models can be called with the corresponding standard SDK and official protocol.

Which agent workspaces does InkRoom MCP support?

InkRoom Remote MCP supports Codex, WorkBuddy, QwenWork and Doubao Work. Codex and WorkBuddy can use agent-managed setup, while QwenWork and Doubao Work use their connector interfaces.

Does reusing a public workflow change the original?

No. Using a public canvas creates an independent copy that you can continue editing and creating from.

How can I check pricing before creating?

The live model directory shows credits and local-currency estimates. Final usage depends on model, resolution, image count and other settings and is confirmed before submission.