Use the Ideogram V3 API via RunAPI with a model skill, unified auth, and pay-as-you-go pricing.
curl -X POST https://runapi.ai/api/v1/ideogram_v3/text_to_image \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "ideogram-v3-text-to-image",
"prompt": "Create a movie poster for 'The Last Frontier' with the title in bold serif at the top, a space station in the background."
}'import { IdeogramV3Client } from "@runapi.ai/ideogram-v3";
const client = new IdeogramV3Client();
const result = await client.textToImage.run({
model: "ideogram-v3-text-to-image",
prompt: "Create a movie poster for 'The Last Frontier' with the title in bold serif at the top, a space station in the background.",
});<?php
require __DIR__ . "/vendor/autoload.php";
use RunApi\IdeogramV3\IdeogramV3Client;
$client = new IdeogramV3Client();
$result = $client->textToImage->run([
'model' => 'ideogram-v3-text-to-image',
'prompt' => 'Create a movie poster for \'The Last Frontier\' with the title in bold serif at the top, a space station in the background.',
]);require "runapi/ideogram_v3"
client = RunApi::IdeogramV3::Client.new
result = client.text_to_image.run(
model: "ideogram-v3-text-to-image",
prompt: "Create a movie poster for 'The Last Frontier' with the title in bold serif at the top, a space station in the background."
)npx skills add runapi-ai/ideogram-v3 -g# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
# Codex
codex plugin install runapi-mcp@agents
# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursorIdeogram V3 is a text-to-image model with strong in-image text rendering accuracy, making it one of the most reliable models for generating images with legible typography. It also supports editing and remix workflows.
| Variant | Billing | Pricing | |
|---|---|---|---|
| ideogram-v3-character | call | $0.18 | View → |
| ideogram-v3-character-edit | call | $0.18 | View → |
| ideogram-v3-character-remix | call | $0.18 | View → |
| ideogram-v3-edit | call | $0.07 | View → |
| ideogram-v3-reframe | call | $0.07 | View → |
| ideogram-v3-remix | call | $0.07 | View → |
| ideogram-v3-text-to-image | call | $0.07 | View → |
| Endpoint | Resolution | Duration | Price | |
|---|---|---|---|---|
| text_to_image | — | — | $0.12-$0.24 / image |
Prices shown for ideogram-v3-character. Other variants retain their own endpoint pricing.
Sign up and generate an API key from the dashboard.
Choose the version that best matches your quality and cost requirements.
Submit your prompt and parameters to the model's documented endpoint.
Poll the task or set a webhook, then download the completed output.
Ideogram V3 is purpose-built for typography in generated images, achieving strong text accuracy. Through RunAPI, all Ideogram V3 endpoints — generation, edit, and remix — share one key.
A single RunAPI API key unlocks the whole model catalog across all providers. No separate accounts to create, no API keys to rotate per integration, and no credential management overhead. Add a new model to your app by changing one parameter.
Per-call pricing in USD, billed monthly into a single invoice. No subscription tiers, no minimum spend, and failed generations are never charged. The pricing page and check_pricing API show exact costs before you commit to a model.
Typed schemas, parameter constraints, and setup notes are packaged in the model skill so your implementation starts from the right contract. The skill loads into Claude Code, Codex, Gemini CLI, Cursor, and VS Code — your agent knows the correct request shape before you write a line of code.
Among the highest text accuracy of any image generation model, especially for posters, logos, and signage.
Output resolution is configurable across landscape, portrait, and square aspect ratios.
A few seconds per image for the standard text-to-image endpoint.
Edit applies targeted modifications to a specific region of an existing image. Remix takes a reference image and regenerates it in a new style guided by your text prompt.
Yes — it can render text in multiple languages within generated images, though accuracy is highest for Latin-script languages.
Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.