Choose Auto, TokenLab Verified, or Official for each request, with prices shown up front. See what's new

Luma AI: UNI-1

UNI-1 is a unified image model in Luma's UNI-1 family for both image creation and precision image editing. It combines text prompting, source-image modification, multi-reference guidance, seed-based reproducibility, and reasoning-informed visual generation in one system, with strong control over composition, identity, style, and visual plausibility.
Compare models
uni-1
AvailableLuma AIImageSync
Price
From $0.0404
Modalities
Image

About UNI-1

UNI-1 is Luma's unified image model that both creates images and edits them. It accepts text prompts and source images, takes multiple reference images, and offers seed-based reproducibility. Luma describes it as an autoregressive model that reasons about intent before it renders. It is the standard variant; UNI-1 Max is the quality-first version.

Where it works well

  • One model for text-to-image and instruction-based editing.
  • Luma documents up to nine reference images to guide style or composition.
  • Responds to camera angle, distance, and light direction instructions.
  • Seed support makes a result repeatable while you vary the prompt.

When to choose another model

  • For the highest-detail final images, UNI-1 Max is the variant Luma tunes for polish.
  • Luma does not present it as a text-rendering or vector tool, so graphic design with dense type may need a specialist model.

Getting started

  1. Create API key

    Create a key in Console, then use it with every model on the platform.

  2. Send your first request

    Copy the example for your language and run it against the endpoint.

    Image editingText to imageTokenLab endpoint
    POST/v1/images/generations
    curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
      -H "Authorization: Bearer sk-xxx" \
      -H "Content-Type: application/json" \
      -d '{
      "operation": "image-to-image",
      "model": "uni-1",
      "prompt": "A minimalist product photo of matte black headphones on a soft blue background.",
      "image_url": "https://example.com/source.png"
    }'

Parameters

Image editing

ParameterValues and limitsDefaultNotes
height1248, 1440, 1504, 1696, 2048, 2464, 2784, 2912, 33602048Use an integer. Use a listed width and height pair: 3360x1248 (3k, 3:1), 2912x1440 (3k, 2:1), 2784x1504 (3k, 16:9), 2464x1696 (3k, 3:2), 2048x2048 (3k, 1:1), 1696x2464 (3k, 2:3), 1504x2784 (3k, 9:16), 1440x2912 (3k, 1:2), 1248x3360 (3k, 1:3).
imageNot providedNot providedAlias of the combined images input. See input_limits.images for the total input image count.
image_urlNot providedNot providedAlias of the combined images input. See input_limits.images for the total input image count.
image_urlsNot providedNot providedAlias of the combined images input. See input_limits.images for the total input image count.
imagesInputs: ≥ 1, ≤ 9Not providedLimits apply when this input is supplied. Image aliases are combined into one input image list; the limit applies to the combined list.
n11Use an integer.
operationRequiredNot providedNot providedNot provided
output_formatjpeg, png, webpNot providedDefault encoding is shared by these equivalent values: jpg, jpeg.
promptNot providedNot providedMinimum length: 2 characters. Maximum length: 6000 characters.
width1248, 1440, 1504, 1696, 2048, 2464, 2784, 2912, 33602048Use an integer. Use a listed width and height pair: 3360x1248 (3k, 3:1), 2912x1440 (3k, 2:1), 2784x1504 (3k, 16:9), 2464x1696 (3k, 3:2), 2048x2048 (3k, 1:1), 1696x2464 (3k, 2:3), 1504x2784 (3k, 9:16), 1440x2912 (3k, 1:2), 1248x3360 (3k, 1:3).

Text to image

ParameterValues and limitsDefaultNotes
height1248, 1440, 1504, 1696, 2048, 2464, 2784, 2912, 33602048Use an integer. Use a listed width and height pair: 3360x1248 (3k, 3:1), 2912x1440 (3k, 2:1), 2784x1504 (3k, 16:9), 2464x1696 (3k, 3:2), 2048x2048 (3k, 1:1), 1696x2464 (3k, 2:3), 1504x2784 (3k, 9:16), 1440x2912 (3k, 1:2), 1248x3360 (3k, 1:3).
imagesNot providedNot providedText-to-image does not accept source images. Do not send this field for that operation. Use one of this model's declared image operations for source-image requests.
n11Use an integer.
operationRequiredNot providedNot providedNot provided
output_formatjpeg, png, webpNot providedDefault encoding is shared by these equivalent values: jpg, jpeg.
promptNot providedNot providedMinimum length: 2 characters. Maximum length: 6000 characters.
width1248, 1440, 1504, 1696, 2048, 2464, 2784, 2912, 33602048Use an integer. Use a listed width and height pair: 3360x1248 (3k, 3:1), 2912x1440 (3k, 2:1), 2784x1504 (3k, 16:9), 2464x1696 (3k, 3:2), 2048x2048 (3k, 1:1), 1696x2464 (3k, 2:3), 1504x2784 (3k, 9:16), 1440x2912 (3k, 1:2), 1248x3360 (3k, 1:3).

Fields outside this contract are rejected.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Image editing

per image
Official price
$0.0404
Verified price
—
Discount
—

Text to image

per image
Official price
$0.0404
Verified price
—
Discount
—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours
Requests
Success rate
P95 latency
Total tokens
Model performance
Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open UNI-1 in Console with a prompt ready to edit or send.

Help me create an image with uni-1 using image-edit at /v1/images/edits. Show the result, cost, and any limits I should know.

Use cases

Best for
  • Text to Image
  • Image editing by instruction

    Change a source photo's lighting, background or object with a plain-language command.

  • Reference-guided style

    Match a house style by supplying several reference pictures alongside a text description of the new scene.

  • Storyboards and comics

    Luma highlights manga and webtoon creation as a strength, with consistent characters across panels.

Prompt examples

Change the time of day in this photo to sunset and add long shadows from the buildings.

A cinematic still of a lone cyclist on a coastal road, low camera angle, backlit, film grain.

Using the three reference images, create a webtoon panel of a girl opening a mysterious door.

FAQ

What is Luma UNI-1?

Luma's unified image model for generation and editing. You can prompt with text, modify an existing image, or guide it with reference images. Luma describes it as reasoning about intent before drawing.

How many reference images can I use?

Luma documents up to nine reference images per request, which can steer style, composition or subject. Use them for style transfer or to hold a character's look across several images.

Can I reproduce a result?

Yes, UNI-1 supports a seed so the same inputs can yield the same image, which helps when you vary only one part of the prompt.

What is the difference from UNI-1 Max?

Same API and capabilities, but UNI-1 Max is tuned for higher output quality when detail matters more than using the default variant. Pick plain UNI-1 for drafts and exploration.

How much does UNI-1 cost?

On TokenLab, UNI-1 costs $0.0404 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should UNI-1 use?

Use https://api.tokenlab.sh/v1/images/edits for UNI-1. The request example below shows the matching code shape.

Which operations does UNI-1 support?

UNI-1 supports Image editing, Text to image. Select an operation above to see its endpoint and request example.

Compare UNI-1

Sources

Reviewed Oct 2, 2026

More from Luma

Related models