Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Luma AI / UNI

UNI-1 Max

Image generation and natural-language editing with reference images and optional web grounding.

Image generation
availableClosed weightsImage generationImage editing
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
12 of 25 specification fields collected
Output resolution2KSee specification notes below
Reference imagesUp to 9 references for generation; source + up to 8 for editingSee specification notes below
Input billingSee ratesLuma Agents API
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)
Output modalities
ImageSource for Output modalities (opens in a new tab)
Reasoning
SupportedSource for Reasoning (opens in a new tab)

Provider-described spatial/visual reasoning. This media API does not expose a language-model reasoning budget or reasoning-token prices.

Tool calling
Not collected

Agent orchestration, hosted GLM tools and built-in web grounding do not establish arbitrary function calling by this model.

Structured output
Not collected

A structured API response envelope is not schema-constrained model text output.

Streaming
Not collected

Polling generation status does not establish progressive output streaming.

Batch processing
Not collected

Asynchronous jobs and concurrent requests do not establish a dedicated Batch API.

Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected

Reusable uploaded media and expiring download links do not establish model-inference caching or discounted cache rates.

Output formats
PNG, JPEGSource for Output formats (opens in a new tab)
Maximum prompt characters
6,000 charactersSource for Maximum prompt characters (opens in a new tab)

Image and image_edit requests require 1–6,000 characters. UNI-1 layering instead accepts 0–500.

Output resolutions
2KSource for Output resolutions (opens in a new tab)

Current pricing says all image requests output at 2048-pixel resolution. A shared SDK image_resolution enum also exposes 1k; its current effect is not confirmed by the image guide.

Aspect ratios
3:1, 2:1, 16:9, 3:2, 1:1, 2:3, 9:16, 1:2, 1:3Source for Aspect ratios (opens in a new tab)
Reference images
Up to 9 references for generation; source + up to 8 for editingSource for Reference images (opens in a new tab)
Input image limits
50 MB and 8000 px per side for URL/base64 image inputsSource for Input image limits (opens in a new tab)
Search grounding
SupportedSource for Search grounding (opens in a new tab)

Optional web_search visual grounding; not arbitrary tool calling.

Product announcement name
UNI-1.1 MaxSource for Product announcement name (opens in a new tab)

The May announcement uses these names while the current API documentation uses uni-1 and uni-1-max. A distinct checkpoint mapping is not verified, so no duplicate release is manufactured.

Image layer extraction
Not supportedSource for Image layer extraction (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Luma Agents API

Provider source (opens in a new tab)
API model ID
uni-1-max
Access
Documented API access; an eligible account, API key and billing setup are required. No paid generation was performed.
Regions
Not collected
API endpoint URL
POST https://agents.lumalabs.ai/v1/generationsSource for API endpoint URL (opens in a new tab)
API operation
imageSource for API operation (opens in a new tab)
Reference images
Up to 9 referencesSource for Reference images (opens in a new tab)
Download URL lifetime
1 hour; polling again can issue a fresh URLSource for Download URL lifetime (opens in a new tab)

URL expiry is not the model-cache TTL or a data-deletion guarantee.

Asynchronous generation
SupportedSource for Asynchronous generation (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Image generationText to image1$0.10image
Image generationImage reference (1 image)1$0.103image
Image generationImage reference (2 images)1$0.106image
Image generationImage reference (3 images)1$0.109image
Image generationImage reference (4 images)1$0.112image
Image generationImage reference (5 images)1$0.115image
Image generationImage reference (6 images)1$0.118image
Image generationImage reference (7 images)1$0.121image
Image generationImage reference (8 images)1$0.124image
Image generationImage reference (9 images)1$0.127image

Rate conditions

  1. Direct Agents API per-image price at the published 2K output setting. Reference-count rows are total prices, not additive fees. Editing reserves one image slot for the source.
Pricing source (opens in a new tab)

Data & enterprise terms

API Terms section 10 commits not to train on covered API inputs or outputs. The pricing page separately labels no-train as a Provisioned Throughput benefit and says no guarantee for pay-as-you-go; this conflict requires contractual confirmation.

Read the service policy (opens in a new tab)

Luma Agents API

Provider source (opens in a new tab)
API model ID
uni-1-max
Access
Documented API access; an eligible account, API key and billing setup are required. No paid generation was performed.
Regions
Not collected
API endpoint URL
POST https://agents.lumalabs.ai/v1/generationsSource for API endpoint URL (opens in a new tab)
API operation
image_editSource for API operation (opens in a new tab)
Reference images
One source + up to 8 referencesSource for Reference images (opens in a new tab)
Download URL lifetime
1 hour; polling again can issue a fresh URLSource for Download URL lifetime (opens in a new tab)

URL expiry is not the model-cache TTL or a data-deletion guarantee.

Asynchronous generation
SupportedSource for Asynchronous generation (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Image generationImage edit (image to image)1$0.103image

Rate conditions

  1. Direct Agents API per-image price at the published 2K output setting. Reference-count rows are total prices, not additive fees. Editing reserves one image slot for the source.
Pricing source (opens in a new tab)

Data & enterprise terms

API Terms section 10 commits not to train on covered API inputs or outputs. The pricing page separately labels no-train as a Provisioned Throughput benefit and says no guarantee for pay-as-you-go; this conflict requires contractual confirmation.

Read the service policy (opens in a new tab)

Luma Agents API

Provider source (opens in a new tab)
API model ID
uni-1-max
Access
Dedicated monthly capacity; minimum 8 units. One unit supplies 1 RPM for UNI-1 or 0.4 RPM for UNI-1 Max; account terms and commitment apply.
Regions
Not collected
API endpoint URL
POST https://agents.lumalabs.ai/v1/generationsSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Provisioned capacity1 month commitment1$3,800.00capacity unit / month
Provisioned capacity3 months commitment1$2,800.00capacity unit / month
Provisioned capacity1 year commitment1$2,100.00capacity unit / month

Rate conditions

  1. Minimum 8 units. Each unit supplies 1 RPM for UNI-1 or 0.4 RPM for UNI-1 Max. Published effective per-image estimates require full utilization and are not pay-as-you-go rates.
Pricing source (opens in a new tab)

Data & enterprise terms

API Terms section 10 commits not to train on covered API inputs or outputs. The pricing page separately labels no-train as a Provisioned Throughput benefit and says no guarantee for pay-as-you-go; this conflict requires contractual confirmation.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Luma Agents API

uni-1-max
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Luma Agents API

uni-1-max
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Luma Agents API

uni-1-max
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inferred from the named Luma-hosted proprietary service, terms restricting access to underlying models and weights, and the separate official public-checkpoint inventory (IMM and TVM). This is release-specific catalog classification, not an assertion that all Luma research is closed.

Classification evidence (opens in a new tab)

Sources reviewed