# Every image model. No API keys.

Source: https://corespeed.io/integrations/image-generation

Image generation gives Claude Code, Codex, Cursor or any MCP agent hundreds of hosted image models through CoreSpeed, with no account or API key for any of them. Your agent searches the models, reads one model's rate and inputs, then generates, edits, upscales or cuts out an image. Each finished image lands in your organization's Drive.

## Set up an agent

Give your agent this line: `set up https://corespeed.io/SKILL.md (read it raw, e.g. with curl)`

It fetches the skill at https://corespeed.io/SKILL.md, adds the CoreSpeed MCP server, signs you in (or up), and keeps the skill for next time. Nothing to connect: Image generation is built in. Each call is priced in credits, from your one balance. Create an account: https://app.corespeed.io/sign-up

## Describe the image. Get the file back

Your agent finds a model that fits, reads its rate and inputs, and runs it. The images come back as links and as files in your Drive.

You ask your agent: "Make three square hero images for our Harbor mug launch: a ceramic mug on a wooden table at sunrise. Tell me the model's rate before you run it."

It calls CoreSpeed:

- `media__list_models`: ok, 412 ms
- `media__get_model`: ok, 198 ms
- `media__generate`: ok, 9420 ms

It reads from: Image generation.

### Generation: Three hero images of the Harbor mug.

The rate was shown before the run. The images are in your Drive for 7 days.

**Done**

- Three square images, a mug on a wooden table at sunrise.

**Next**

- Move the one you like out of tmp/ to keep it.
- Or turn it into a short video.

_Illustrative example · Fictional product and images_

How media generation works: https://corespeed.io/docs/media

## From a prompt to a file in Drive

Requests you can make right after setup. The data is fictional.

### Pick a model by its rate

Three text to image models · Rates read first

- Asked for: Photoreal, square, under budget
- Shown: Each model with its rate
- Nothing run yet

### Edit an image you already have

Swap the background · From a Drive file

- Input: brand/mug-studio.png
- Change: Studio white to a kitchen counter
- A new file · The original stays

### Turn the still into video

From hero image to clip · Image + video

- Start from: The hero image's Drive path
- Make: A five-second clip
- No download, no re-upload

Full example: https://corespeed.io/integrations/video-generation (Markdown: https://corespeed.io/integrations/video-generation.md)

## Keep your agent. Nothing to connect

One CoreSpeed account, across compatible agents.

1. **Set up CoreSpeed**: Give your agent the setup line. It adds CoreSpeed and signs you in.
2. **Check the price**: Every tool has a rate in credits. Your agent reads it before each call.
3. **Start with one task**: Ask for one image, and ask your agent to show the model's rate first.

Setup guides: Claude Code https://corespeed.io/docs/mcp#claude-code · Codex https://corespeed.io/docs/mcp#codex · Cursor https://corespeed.io/docs/mcp#cursor

## Questions

### Which image models can my agent use?

Hundreds of hosted models for text to image, editing, upscaling and background removal. The catalog page lists each one with its rate. Every image model: https://corespeed.io/catalog/image-generation

### Am I charged if a generation fails?

No. A generation is billed once, after it succeeds. Failed, cancelled and expired generations are never charged.

### Can I use my own image as an input?

Yes. Give a public https link or a file in your Drive. Your agent can upload a local file to Drive first.

### Do I need an account or API key for Image generation?

No. Image generation is built into CoreSpeed. Your agent sees its tools after setup, with nothing to connect.

### What does Image generation cost?

Each call has a rate in credits, shown before it runs, from your one balance. A failed call costs nothing. Every Image generation tool and its price: https://corespeed.io/catalog/image-generation

### Do I have to switch agents?

No. CoreSpeed adds tools to the agent you already use: Claude Code, Codex, Cursor, or another MCP client. Each one signs in once.

Every tool and price: https://corespeed.io/catalog/image-generation

## Related pages

- [Drive](https://corespeed.io/docs/drive): A file system for your agents: every file a tool takes or produces lives at a path in your organization's Drive, mountable as an S3 bucket.
- [Media understanding for AI agents](https://corespeed.io/integrations/media-understanding): Let your agent watch a video, look at an image or listen to audio, and answer your question in text. Files from Drive, a link or YouTube.
- [Tools](https://corespeed.io/tools): Models, the live web and nine social platforms, on one balance. No account for any of them.
- [Video generation for AI agents](https://corespeed.io/integrations/video-generation): Give your agent hundreds of text to video and image to video models, with no API keys. It reads the rate first, and long renders finish as jobs.

## Sources

- Media docs: https://corespeed.io/docs/media
- Image generation catalog: https://corespeed.io/catalog/image-generation
- Generating launch images and short videos from an agent: https://corespeed.io/blog/generate-launch-assets-with-media-tools

Reviewed 2026-11-14.

## Links

- Product overview: https://corespeed.io/ (Markdown: https://corespeed.io/index.md)
- All integrations: https://corespeed.io/integrations (Markdown: https://corespeed.io/integrations.md)
- Documentation: https://corespeed.io/docs
- Pricing: https://corespeed.io/pricing (Markdown: https://corespeed.io/pricing.md)
