Spiral gives your agent every tool with one account. Browse the tools →

Gemini CLI · ImageReleased 2026-02-17

How to Use Recraft V4 in Gemini CLI

Recraft V4 makes raster illustrations, campaign concepts, and photographic images from text. Its 1024×1024 square output suits visual exploration, while Recraft V4 Pro provides 2048×2048 output for more detailed work.

Prompts to try with Recraft V4 in Gemini CLI

Copy an example into Gemini CLI, or ask in your own words.

Read the homepage copy and use Recraft V4 to create a 1024×1024 editorial illustration of its central idea. Put the subject on the right, leave the left open for HTML text, and save the image with the project assets.

Recraft V4Gemini CLI
Try asking
  • Read the latest blog draft and use Recraft V4 to create a 1024×1024 cover illustration. Choose one concrete scene from the article, use the site's palette, and keep all lettering in HTML.

  • Use Recraft V4 to create a 1024×1024 illustration for the empty reading list screen: a fox asleep beside a stack of books, flat shapes, dark green and white, centered composition. Save it and check its appearance at the component's display size.

  • Use Recraft V4 to create a 2048×2048 hero image for the ceramics shop in this project: a handmade charcoal bowl on a stone surface, side lighting, visible glaze texture, and open space above. Add it to the homepage and preview the crop.

  • Use Recraft V4 to create 2048×2048 artwork for the project's jazz event page: a close view of a brass trumpet, hard light from the upper left, and the short headline 'NIGHT SESSION'. Check the lettering before adding it.

How to set up Recraft V4 in Gemini CLI

Pick the way that suits you. Each takes about two minutes.

Use Spiral's MCP server

  1. Add the server

    Or add it to ~/.gemini/settings.json yourself:

    gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
  2. Sign in

    Start gemini and run:

    /mcp auth spiral
  3. Check it

    In Gemini CLI, run /mcp. From your shell:

    gemini mcp list

Use the Spiral skill

  1. Send Gemini CLI this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. Install and sign in

    Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Recraft V4

    One request; the result comes back by polling or a webhook.

    curl https://api.spiral.ai/v1/runs \
      -H "Authorization: Bearer $SPIRAL_API_KEY" \
      -H "Content-Type: application/json" \
      -H "Idempotency-Key: $(uuidgen)" \
      -d '{
        "provider": "fal",
        "model": "fal-ai/recraft/v4/text-to-image",
        "input": {
          "prompt": "Tilt-shift miniature effect on a real Portuguese fishing village at golden hour, colorful boats in the harbor appearing toy-like, selective focus band across…"
        }
      }'

Then paste one of the prompts above: Gemini CLI finds Recraft V4 on Spiral, shows the price and runs it.

Recraft V4 providers and prices

Spiral runs Recraft V4 through fal. Open a card for today's price, with every fee included.

falImage
Recraft V4 Normal · Text to Image
fal-ai/recraft/v4/text-to-image

What can you do with Recraft V4 in Gemini CLI?

Create website artwork from the project's written design brief and place it in the page layout. A coding agent can turn existing copy into a visual prompt and check the result in context.

Website hero artwork

Generate a photographic scene or illustration with the subject to one side and open space for a headline added in the page layout.

Campaign concept exploration

Try different subjects, lighting directions, and compositions before choosing an image direction for a campaign.

Editorial illustrations

Turn an article's central idea into a specific illustrated scene with a defined palette and focal point.

Product photography concepts

Describe a product, surface, material, and lighting setup to explore a proposed photo shoot.

Event poster concepts

Combine an illustrated or photographic subject with a short event headline. Proofread the rendered text before preparing the final layout.

Social post artwork

Create square campaign images around a recurring written brief for palette, framing, and lighting.

Questions about Recraft V4 in Gemini CLI

Can Gemini CLI use Recraft V4?

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Recraft V4 like any built-in tool.

How much does Recraft V4 cost in Gemini CLI?

$0.052 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.

Do I need a fal account to use Recraft V4 in Gemini CLI?

No. Spiral runs Recraft V4 on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up Recraft V4 in Gemini CLI?

About two minutes: add the server, then sign in, then check it.

Does Gemini CLI wait while Recraft V4 runs?

Recraft V4 runs in the background. Gemini CLI starts the run, checks on it and gives you the image when it's ready.

What is Recraft V4 good at?

Recraft V4 suits photographic campaign concepts, illustrations, and graphics with short text. Give it a clear subject, composition, and lighting direction when the image needs to follow a specific brief.

How does Recraft V4 Pro differ from Recraft V4?

Recraft V4 produces 1024×1024 square images; Recraft V4 Pro produces 2048×2048 square images. Use Recraft V4 for exploration and Recraft V4 Pro when finer detail matters.

Can Recraft V4 put readable text in an image?

Yes, Recraft documents support for short and medium-length phrases. Keep poster headlines and packaging copy brief, then check the generated wording before using it.

Should a Recraft V4 prompt be short or detailed?

Use a short prompt to explore visual directions. For a defined result, describe the subject and setting first, then placement, lighting, camera angle, and mood.

What should I check before using a generated image?

Inspect small faces and hands for distorted anatomy, and proofread any text. Recraft describes stronger anatomy and realism in Recraft V4 Pro, but inspection remains a useful final step.

Get started

Start using Recraft V4 in Gemini CLI

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Gemini CLI:

Set up Gemini CLI

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options