How to Use Ideogram 3.0 Text to Image in Codex
Ideogram 3.0 Text to Image creates posters, logo concepts, and images with readable lettering from a written brief. Unlike Ideogram 3.0 Remix, it can start without an existing image.
Prompts to try with Ideogram 3.0 Text to Image in Codex
Copy an example into Codex, or ask in your own words.
Read the homepage copy and use Ideogram 3.0 Text to Image to create a square launch graphic. Use the product name as the only lettering, with a paper-cut illustration based on its main purpose. Save the result with the project's image assets.
Use Ideogram 3.0 Text to Image to draft a 1024 by 1024 pixel graphic for the release notes page. Put "WHAT'S NEW" above a hand-painted toolbox illustration. Use the project's accent color and turn off automatic prompt expansion.
Generate a product photo with Ideogram 3.0 Text to Image: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first. Save the result in ./assets.
Make four logo concepts for a coffee brand called "Northline" with Ideogram 3.0 Text to Image.
Create a 16:9 hero image of a quiet mountain cabin at dusk with Ideogram 3.0 Text to Image.
How to set up Ideogram 3.0 Text to Image in Codex
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
codex mcp add spiral --url https://api.spiral.ai/mcp
- Sign in
Codex opens the browser: sign in to Spiral and click Authorize. No API key. codex mcp list then shows Spiral.
codex mcp login spiral
Use the Spiral skill
- Send Codex this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- 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
- Create an API key
In the console, under API keys.
- Run Ideogram 3.0 Text to Image
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/ideogram/v3", "input": { "prompt": "The Bone Forest stretched across the horizon, its trees fashioned from the ossified remains of ancient leviathans that once swam through the sky. Shamans with…" } }'
Then paste one of the prompts above: Codex finds Ideogram 3.0 Text to Image on Spiral, shows the price and runs it.
Ideogram 3.0 Text to Image providers and prices
Spiral runs Ideogram 3.0 Text to Image through fal. Open a card for today's price, with every fee included.
$0.039 per image with TURBO, $0.078 with BALANCED (the default), $0.117 with QUALITY.
Settings you can ask for
Ideogram 3.0 Text to Image works from your image URLs and prompt. Ask Codex for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Rendering speed | TURBO, BALANCED, or QUALITY | BALANCED | The rendering speed to use. |
| Style | AUTO, GENERAL, REALISTIC, or DESIGN | The style type to generate with. Cannot be used with style_codes. | |
| Expand prompt | on or off | on | Determine if MagicPrompt should be used in generating the request or not. |
| Number of images | 1 to 8 | 1 | Number of images to generate. |
| Seed | a whole number | Seed for the random number generator | |
| Style preset | 80S_ILLUSTRATION, 90S_NOSTALGIA, ABSTRACT_ORGANIC, ANALOG_NOSTALGIA, ART_BRUT, ART_DECO, ART_POSTER, AURA and 54 more | Style preset for generation. The chosen style preset will guide the generation. | |
| Negative prompt | what to leave out, in words | Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. |
Every API field of Ideogram Text to Image is on its tool page: open its card above.
What can you do with Ideogram 3.0 Text to Image in Codex?
Create graphics and short lettering for the interface you are building with Ideogram 3.0. A coding agent can turn project copy and visual requirements into focused briefs, then place reviewed artwork in the project.
Logo concepts
Explore a simple symbol and a short business name. Use transparent output when the mark will sit over different backgrounds, and inspect the lettering before refining the design.
Sticker artwork
Create a single illustrated subject with a short phrase and a clear silhouette. Transparent output gives you artwork to place on a sticker layout.
Apparel graphics
Draft a chest graphic built around an illustration and a few words. Check the artwork's pixel dimensions against the printer's requirements before production.
Icons and clip art
Create individual illustrations for presentations, onboarding screens, or educational materials. Request the same colors, line weight, and viewing angle across the set.
Event poster drafts
Generate a poster around a short event title, a clear focal illustration, and a limited palette. Add dense schedules and other small text afterward.
More on Ideogram 3.0 Text to Image and Codex
Overview
Ideogram 3.0 Text to Image in other agents
Questions about Ideogram 3.0 Text to Image in Codex
Can Codex use Ideogram 3.0 Text to Image?
Yes. Add Spiral to Codex as an MCP server, and Codex can find and run Ideogram 3.0 Text to Image like any built-in tool.
How much does Ideogram 3.0 Text to Image cost in Codex?
$0.039 per image. Billed on `num_images`, default 1. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.
Do I need a fal account to use Ideogram 3.0 Text to Image in Codex?
No. Spiral runs Ideogram 3.0 Text to Image on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Ideogram 3.0 Text to Image in Codex?
About two minutes: add the hosted server, then sign in.
Does Codex wait while Ideogram 3.0 Text to Image runs?
Ideogram 3.0 Text to Image runs in the background. Codex starts the run, checks on it and gives you the image when it's ready.
What is Ideogram 3.0 good at?
Graphics that combine imagery with short, readable lettering are a useful starting point: logo concepts, headlines, badges, and promotional artwork. It also handles realistic imagery.
Can Ideogram 3.0 render exact wording?
Put the exact words in quotation marks and describe their position. Check every result for spelling errors, especially when the text is long or the scene is crowded.
Which languages work best?
English gives the most reliable results, especially for lettering. Accented letters and non-Latin scripts can render incorrectly or disappear.
How long should an Ideogram 3.0 prompt be?
Aim for fewer than about 150 words. Put the main subject and essential wording first, then describe placement, lighting, and style.
When should I turn off Magic Prompt?
Turn it off when your brief already specifies the wording and visual details you want. Leave it on when you want a short idea expanded with additional detail.
Start using Ideogram 3.0 Text to Image in Codex
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Codex:
set up https://spiral.ai/SKILL.md


