Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Ideogram / Ideogram 4

Ideogram 4.5

Image generation and precise editing that preserves unchanged source pixels.

Image generation
availableClosed weightsImage generationImage editing
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
8 of 22 specification fields collected
Output resolutionGeneration: supported 1K/2K presets; precise editing follows the source size with possible downscalingSee specification notes below
Reference imagesGenerate/edit: up to 5 source images; precise edit: one source plus up to 4 referencesSee specification notes below
Input billingNot collectedIdeogram
Output billingNot collectedNo inferred price

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
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
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
Reference images
Generate/edit: up to 5 source images; precise edit: one source plus up to 4 referencesSource for Reference images (opens in a new tab)

With a mask, at most three extra references. Each file is at most 25 MB.

Input image formats
JPEG, PNG, WEBPSource for Input image formats (opens in a new tab)
Output resolutions
Generation: supported 1K/2K presets; precise editing follows the source size with possible downscalingSource for Output resolutions (opens in a new tab)

Exact sizes require multiples of 32, at least 256 pixels per side and at most 2048 × 2048 total pixels. Source-preserving editing is a separate case.

Aspect ratios
Source images: 1:6 through 6:1Source for Aspect ratios (opens in a new tab)
Mask input
SupportedSource for Mask input (opens in a new tab)

Black marks the edited region; white marks the preserved region. Mask dimensions must match the source.

Structured prompt input
SupportedSource for Structured prompt input (opens in a new tab)

Structured JSON prompt input does not establish structured JSON model output.

Access & pricing

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

Ideogram

Provider source (opens in a new tab)
API model ID
ideogram-4-5
Access
Documented API route; account, API key, prepaid credits and applicable permissions required.
Regions
Not collected
API endpoint URL
POST https://api.ideogram.ai/v2/image/precise-edit/ideogram-4-5Source for API endpoint URL (opens in a new tab)
API request fields
dry_run, prompt, image, reference_images, mask, quality, seed, num_images, enable_copyright_detection, async, webhook_urlSource for API request fields (opens in a new tab)
Request price quote
SupportedSource for Request price quote (opens in a new tab)

dry_run validates and quotes the request without generation, storage or billing; authentication still applies.

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

Polling/webhooks, not streamed image output or proof of a separate Batch API.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Ideogram

Provider source (opens in a new tab)
API model ID
ideogram-4-5
Access
Documented API route; account, API key, prepaid credits and applicable permissions required.
Regions
Not collected
API endpoint URL
POST https://api.ideogram.ai/v2/image/generate/ideogram-4-5Source for API endpoint URL (opens in a new tab)
API request fields
dry_run, prompt, magic_prompt, images, mask, size, quality, seed, num_images, enable_copyright_detection, async, webhook_urlSource for API request fields (opens in a new tab)
Request price quote
SupportedSource for Request price quote (opens in a new tab)

dry_run validates and quotes the request without generation, storage or billing; authentication still applies.

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

Polling/webhooks, not streamed image output or proof of a separate Batch API.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

fal

Provider source (opens in a new tab)
API model ID
ideogram/v4.5
Access
fal-hosted model; eligible account, API key and host-specific billing apply.
Regions
Not collected

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Image generationLow1$0.03image
Image generationMedium1$0.06image
Image generationHigh1$0.22image

Rate conditions

  1. fal text-to-image rate. The published host page says image size does not change this price. Do not substitute this for direct Ideogram size-tiered billing.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

fal

Provider source (opens in a new tab)
API model ID
ideogram/v4.5/edit
Access
fal-hosted model; eligible account, API key and host-specific billing apply.
Regions
Not collected

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Image generationVery Low1$0.008image
Image generationLow1$0.03image
Image generationMedium1$0.06image
Image generationHigh1$0.22image

Rate conditions

  1. fal image-editing rate. The published host page says image size does not change this price. Do not substitute this for direct Ideogram size-tiered billing.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

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.

Ideogram

ideogram-4-5
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.

Ideogram

ideogram-4-5
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.

fal

ideogram/v4.5
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.

fal

ideogram/v4.5/edit
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 this specifically named hosted release and the official weight inventory, which publishes 4.0 checkpoints only. The provider explicitly identifies 4.0 as open-weight; that classification is not copied to other versions. This dated inference requires review when additional weights are released.

Classification evidence (opens in a new tab)

Sources reviewed