Ideogram V3 - Kyma API

Overview

Ideogram V3 is a text-to-image model from Ideogram that specializes in generating legible, correctly spelled text within images. It accepts text prompts and outputs raster images, making it a focused tool for typographic design tasks. On Kyma, the model runs through an OpenAI-compatible endpoint with a single API key. It supports prompt caching, which bills repeated prompt prefixes at this model’s cached input rate, and includes automatic request failover. Exact costs are returned in the usage.cost field, and the X-Kyma-Model header reports the active model. The model does not support image input, reasoning traces, or structured JSON outputs. It operates at a medium speed tier and is billed per image at a premium cost level.

Specs

Field	Value
Model ID	`ideogram-v3`
Best for	Typography, packaging, posters, logos
Context window	0
Input modalities	Text
Output modalities	Image
Tool calling	Yes
Structured outputs	Yes
Prompt caching	Yes
Speed	Medium
Cost band	Premium
Release stage	Stable

Pricing

	Per 1M tokens
Input	$0.20
Output	$0.60

Use this when

Typography and Poster Design — Generates posters and banners with correctly spelled, well-formatted text.
Product Packaging Mockups — Creates packaging visuals with accurate brand names and label text.
Logo Concept Generation — Produces logo drafts that integrate custom text cleanly into graphic elements.
Marketing Asset Creation — Builds promotional images where headline text must render precisely.

Not ideal for

Avoid this model for general-purpose photography, image-to-image editing, or workflows that require structured JSON outputs or vision input.

Pick something else when

You need photorealistic scene generation: use imagen-4-ultra.
You require high-speed batch generation: use imagen-4-fast.
You need scalable vector design assets: use recraft-v4-vector.
You want balanced quality for general art: use flux-2-pro.

Example

from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="ideogram-v3",
    messages=[{"role": "user", "content": "..."}],
)

Agent query example

Ask the API which models fit, instead of hardcoding an id:

curl "https://kymaapi.com/v1/models?recommended_for=generate-images&tools=true&quality_tier=frontier-open"

FAQ

Does this model accept image inputs? No, it only accepts text prompts and outputs images. How are requests billed on Kyma? Requests are billed per image, with exact costs returned in the usage.cost field. Can I cache prompts to reduce costs? Yes, prompt caching is supported and bills repeated prefixes at this model’s cached input rate.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ