Loading model…正在加载模型详情…
IdeogramGenerate images from a prompt with Ideogram V3, Ideogram's model for realistic scenes and typography-led designs.
- From $0.02 / image
- 1:1, 16:9 or 9:16
Examples
A cinematic photograph of a tranquil lakeside at twilight, viewed from a slight elevation. In the center, a cluster of softly glowing reeds and water lilies emit a gentle, golden light, their reflections shimmering on the calm surface. The elegant neon-style white text ‘{{appName}}’ hovers just above the water, subtly illuminated and harmonizing with the natural glow. Surrounding willows and drifting mist frame the scene, creating a serene yet magical atmosphere, with warm highlights contrasting against the cool blues of the evening sky.
This image has a bold, bright blue-purple gradient background reflecting {{appName}}’s brand colors, with the word “{{appName}}” in sleek white lettering near the top-left corner. Below it, large block letters arranged in a colorful grid spell out the phrase “CREATE WITH {{appName}}.” Each letter sits against a vibrant background color—electric blue, neon pink, vivid purple, bright yellow, teal, or black—giving the design a lively, modern patchwork look. All rows of letters are evenly spaced within a neat rectangular area. One block to the right features a stylized AI circuit icon in white. At the bottom of the image, a bold white question mark adds a playful invitation. The overall style blends pop-art energy with a clean, tech-inspired design, using eye-catching typography and high-contrast colors.
A surreal underwater portrait composition featuring a woman surrounded by silver and golden fish. The subject has striking blue eyes, defined eyebrows, and pale skin with a matte complexion. Multiple small to medium-sized fish float around the face - some are silvery-white and red, others have metallic golden scales, and one has pink-orange coloring with spiky fins. The background is a deep blue underwater setting with subtle lighting effects. The composition is angled with the fish arranged asymmetrically around the face. The image has a high fashion photography aesthetic with the dreamlike quality.
What is Ideogram V3?
Ideogram V3 is an image model from Ideogram. Ideogram describes it as combining realistic image generation with text rendering and control over composition.
UniRoute offers the text-to-image variant. Describe the image you want, including any words and their placement, then choose an aspect ratio. The request uses the catalog option shown in the workspace.
Ideogram describes V3 as offering realistic lighting, stronger text rendering and more consistent creative control. The UniRoute workspace keeps the available text-to-image inputs together, while the specs table lists the callable options.
What you can do
What you can do with Ideogram V3 through UniRoute today.
Text to image
Describe the subject, style, composition and any wording you want in the image. Choose an available option and review the quote before running.
Other Ideogram V3 modes and controls (editing, remixing, reframing, style references and rendering modes) are not available on UniRoute yet.
Specs & variants
The variants you can call, with their options and prices.
| Variant | Model ID | Modes | Inputs | Output | Price |
|---|---|---|---|---|---|
| Ideogram V3 | ideogram/v3-text-to-image | Text to image | Text prompt and an option for aspect ratio | Aspect ratio: 1:1, 16:9, 9:16 | $0.02 per request |
Pricing
Priced per request. The option you choose sets the price.
| Ideogram V3 | |
|---|---|
| 1:1 | $0.02 |
| 16:9 | $0.02 |
| 9:16 | $0.02 |
Rounded to the cent; the live quote in the workspace shows the exact amount. Prices updated 2026-11-08.
Pay as you go from a single USD wallet balance. You see the quote before each request.
API
Call Ideogram V3 from your own code with the media API.
cURL
# Requires bash, curl and jq. Set API_KEY to your own unified UniRoute Key.set -euo pipefail: "${API_KEY:?Set API_KEY first}"BASE='https://api.uniroute.app/v1/media'MODEL='ideogram/v3-text-to-image'OPTION='square_hd'PROMPT='A calm sunrise over a mountain lake'curl -fsS --max-time 60 "$BASE/catalog" -H "Authorization: Bearer $API_KEY" | jq -e '.data.models'BODY=$(jq -n --arg model "$MODEL" --arg option "$OPTION" --arg prompt "$PROMPT" '{model:$model,option:$option,prompt:$prompt}')QUOTE_BODY=$(printf '%s' "$BODY" | jq '{model,option}')QUOTE=$(curl -fsS --max-time 60 "$BASE/quote" -H "Authorization: Bearer $API_KEY" -H 'Content-Type: application/json' -d "$QUOTE_BODY")CAP=$(printf '%s' "$QUOTE" | jq -er '.data.quoted_usd')BODY=$(printf '%s' "$BODY" | jq --arg cap "$CAP" '. + {max_cost_usd:$cap}')IDEMPOTENCY="example-$(date +%s)-$$"create() { curl -fsS --max-time 60 "$BASE/tasks" -H "Authorization: Bearer $API_KEY" -H "Idempotency-Key: $IDEMPOTENCY" -H 'Content-Type: application/json' -d "$BODY"; }TASK_ID=$(create | jq -er '.data.task_id')# The same request and idempotency key must return the original task without charging again.REPLAY_ID=$(create | jq -er '.data.task_id')[ "$TASK_ID" = "$REPLAY_ID" ]for attempt in $(seq 1 120); do TASK=$(curl -fsS --max-time 60 "$BASE/tasks/$TASK_ID" -H "Authorization: Bearer $API_KEY") printf '%s' "$TASK" | jq -e '.data | {task_id,status,billing}' if printf '%s' "$TASK" | jq -e '.data.status == "success" and .data.billing.state == "charged"' >/dev/null; then index=0 while IFS= read -r url; do index=$((index+1)) curl -fL --max-time 120 "$url" -o "$TASK_ID-$index.bin" done < <(printf '%s' "$TASK" | jq -er '.data.urls[].url') break fi if printf '%s' "$TASK" | jq -e '.data.status == "failed" and .data.billing.state == "released"' >/dev/null; then exit 1; fi if [ "$attempt" = 120 ]; then echo "Polling limit reached. Keep task ID $TASK_ID and query it later; do not create a new task." >&2 exit 1 fi sleep 5donecurl -fsS --max-time 60 "$BASE/tasks?limit=20" -H "Authorization: Bearer $API_KEY" | jq -e '.data'# Check this task and the caller Key in Console usage; billing.charged_usd is the actual USD charge.Parameters
| Name | In | Description |
|---|---|---|
model | Body | Model ID to run. |
option | Body | One of the options offered for the model: square_hd, landscape_16_9, portrait_16_9. |
prompt | Body | Text prompt describing what to generate. |
max_cost_usd | Body | Maximum cost in USD for this task, taken from the quote. |
Idempotency-Key | Header | A unique key per task, so a repeated request returns the original task instead of charging again. |
Guides
Use cases
Typical ways to put Ideogram V3 to work.
Posters and lettering
Explore a poster with a headline, supporting text and a clear visual hierarchy described in the prompt.
Brand graphics
Draft logo ideas, labels and campaign graphics with the words and composition specified in writing.
Realistic scenes
Describe lighting, perspective and the environment to develop a visual concept for editorial or commercial work.
FAQ
Common questions about Ideogram V3.
What is Ideogram V3?
Ideogram V3 is an image model from Ideogram. Ideogram describes it as combining realistic image generation with text rendering and control over composition.
Which Ideogram V3 variant can I use?
The callable variant here is ideogram/v3-text-to-image. The variant row and specs table show only the model you can run on UniRoute today.
Which settings can I choose?
Choose an aspect ratio. UniRoute does not expose a rendering-speed selector, style references or image inputs for this variant.
How much does Ideogram V3 cost?
From $0.02 / image. Each request is quoted for the variant and option you select. The Pricing section lists every available request price (prices updated 2026-11-08).
Can I upload a reference image?
No. This UniRoute workspace currently takes a text prompt and the catalog option shown above. Reference-image inputs are not available for the variants listed here.
How do I call Ideogram V3 from code?
Use the media API: request a quote for your model and option, create a task with an Idempotency-Key and a maximum cost, then poll the task until the result is ready. The API section shows a complete example and the parameters.
Is there a free trial or free credits?
No. Generation is paid from your wallet balance. You can open the workspace and review the price without paying, create an account to see a live quote for your exact settings, and you are charged only for requests that are accepted.
Related models
Other versions, models from the same provider and alternatives.
