Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Pruna AI / P-Image

P-Image-Ideogram

Joint Pruna and Ideogram text-to-image model with five quality levels. Native Pruna, Replicate and Ideogram APIs expose different request controls.

Image generation
availableClosed weightsImage generation
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
7 of 22 specification fields collected
Output resolution1K, 2KSee specification notes below
Output formatsPNG, JPEG, WebPSee specification notes below
Input billingSee ratesPruna 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

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Maximum input tokens
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Maximum output
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Maximum prompt characters
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Reasoning
SupportedSource for Reasoning (opens in a new tab)

Provider exposes image-generation compute/quality levels. This is not a general-purpose reasoning or reasoning-trace claim.

Tool calling
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Structured output
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Streaming
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Batch processing
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Fine-tuning
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Context caching
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Knowledge cutoff
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Release date
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Parameters
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Architecture
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Languages
Not collected

Not established for this exact model or managed component. General chat capabilities are not inferred from a media API.

Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
ImageSource for Output modalities (opens in a new tab)
Developed by
Pruna AI, IdeogramSource for Developed by (opens in a new tab)
Output resolutions
1K, 2KSource for Output resolutions (opens in a new tab)
Output formats
PNG, JPEG, WebPSource for Output formats (opens in a new tab)
Structured prompt input
Accepts a JSON string as the image prompt, including layout and color instructions. This is structured input, not schema-constrained generated JSON.Source for Structured prompt input (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.

Pruna API

Provider source (opens in a new tab)
API model ID
p-image-ideogram
Access
Hosted API; account and API key required. No generation was submitted.
Regions
Not established
API endpoint URL
POST https://api.pruna.ai/v1/predictionsSource for API endpoint URL (opens in a new tab)
Authentication
apikey and Model headers; request fields are nested under input.Source for Authentication (opens in a new tab)
Model controls
seed, width, height, prompt, thinking, image_size, aspect_ratio, output_format, output_quality, prompt_upsamplingSource for Model controls (opens in a new tab)
Required request fields
promptSource for Required request fields (opens in a new tab)

OpenAPI required-field list; conditional requirements in property descriptions are recorded separately.

Request quotas
500 requests/minuteSource for Request quotas (opens in a new tab)
Asynchronous generation
Asynchronous by default. Try-Sync=true waits up to 60 seconds; a prediction ID and status URL support longer jobs.Source for Asynchronous generation (opens in a new tab)
Result retrieval
GET /v1/predictions/status/{id}; download the result from the returned URL.Source for Result retrieval (opens in a new tab)
Supported reasoning efforts
very low, low, medium, high, very highSource for Supported reasoning efforts (opens in a new tab)
Generation controls
thinking defaults to high; image_size defaults to 1K; aspect_ratio defaults to 1:1.Source for Generation controls (opens in a new tab)
Aspect ratios
1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, customSource for Aspect ratios (opens in a new tab)
Resolution controls
Custom width and height each at most 2560 px, default 1024, rounded to multiples of 16. image_size is ignored for custom dimensions.Source for Resolution controls (opens in a new tab)

Schema minimum is zero; this does not establish usable zero-pixel output.

Prompt expansion
prompt_upsampling defaults to true; false passes the original prompt.Source for Prompt expansion (opens in a new tab)
Seed control
Optional integer seed; no numerical bounds in this schema.Source for Seed control (opens in a new tab)
Image quality settings
output_quality: 0–100, default 80, ignored for PNG. output_format defaults to jpg.Source for Image quality settings (opens in a new tab)
Documentation discrepancy
Older product configuration table lists four levels and default medium. Native OpenAPI and the API guide agree on five space-separated values with default high.Source for Documentation discrepancy (opens in a new tab)
Pricing coverage
Ten native tiers by thinking and 1K/2K size. Custom-dimension tier mapping is not published here.Source for Pricing coverage (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Image generationvery low · 1K1$0.003image
Image generationvery low · 2K2$0.006image
Image generationlow · 1K3$0.0075image
Image generationlow · 2K4$0.015image
Image generationmedium · 1K5$0.01image
Image generationmedium · 2K6$0.02image
Image generationhigh · 1K7$0.015image
Image generationhigh · 2K8$0.03image
Image generationvery high · 1K9$0.033image
Image generationvery high · 2K10$0.066image

Rate conditions

  1. Native Pruna thinking=very low, image_size=1K. Custom-dimension billing is not inferred.
  2. Native Pruna thinking=very low, image_size=2K. Custom-dimension billing is not inferred.
  3. Native Pruna thinking=low, image_size=1K. Custom-dimension billing is not inferred.
  4. Native Pruna thinking=low, image_size=2K. Custom-dimension billing is not inferred.
  5. Native Pruna thinking=medium, image_size=1K. Custom-dimension billing is not inferred.
  6. Native Pruna thinking=medium, image_size=2K. Custom-dimension billing is not inferred.
  7. Native Pruna thinking=high, image_size=1K. Custom-dimension billing is not inferred.
  8. Native Pruna thinking=high, image_size=2K. Custom-dimension billing is not inferred.
  9. Native Pruna thinking=very high, image_size=1K. Custom-dimension billing is not inferred.
  10. Native Pruna thinking=very high, image_size=2K. Custom-dimension billing is not inferred.
Pricing source (opens in a new tab)

Data & enterprise terms

Pruna API terms retain customer ownership of input/output and permit processing to provide the service. Operational telemetry is used for security and service improvement. A universal retention period and zero-training guarantee are not established.

Read the service policy (opens in a new tab)

Replicate

Provider source (opens in a new tab)
API model ID
prunaai/p-image-ideogram
Access
Hosted API; account and API key required. No generation was submitted.
Regions
Not established
API endpoint URL
POST https://api.replicate.com/v1/predictionsSource for API endpoint URL (opens in a new tab)
Authentication
Bearer API token. Supply the model/version and an input object.Source for Authentication (opens in a new tab)
Model revision
1962cf4c5b3618d9e116fd92f93a0a0aa650ea6c9592a673e6cb6e41a337c1dcSource for Model revision (opens in a new tab)

Published deployment revision, not the model launch date.

Model selection
Version-pinned selector prunaai/p-image-ideogram:1962cf4c5b3618d9e116fd92f93a0a0aa650ea6c9592a673e6cb6e41a337c1dcSource for Model selection (opens in a new tab)
Model controls
seed, width, height, prompt, thinking, image_size, aspect_ratio, output_format, output_quality, prompt_upsamplingSource for Model controls (opens in a new tab)
Required request fields
promptSource for Required request fields (opens in a new tab)
Asynchronous generation
Prediction API; Prefer: wait can wait up to 60 seconds, with status polling for unfinished jobs.Source for Asynchronous generation (opens in a new tab)
Output formats
png, jpg, webpSource for Output formats (opens in a new tab)
Result metadata
The model output schema is an image URI.Source for Result metadata (opens in a new tab)
Request quotas
Not collected

No model-specific Replicate request quota established; Pruna native quotas are not inherited.

Supported reasoning efforts
very low, low, medium, high, very highSource for Supported reasoning efforts (opens in a new tab)
Generation controls
thinking defaults to high; image_size=1K; aspect_ratio=1:1. prompt_upsampling defaults to true.Source for Generation controls (opens in a new tab)
Resolution controls
Custom dimensions up to 2560 px, rounded to multiples of 16; image_size ignored for custom sizing.Source for Resolution controls (opens in a new tab)
Image quality settings
JPEG default; quality 0–100, default 80, ignored for PNG.Source for Image quality settings (opens in a new tab)
Billing basis
Published current billing configuration supplies the host-specific image tariffs. Very High differs from native Pruna.Source for Billing basis (opens in a new tab)
Documentation discrepancy
Very High billing criteria use very-high, while the request enum uses very high. One tier title says High despite a Very High description. Preserve the request schema spelling and label this tariff by its criteria.Source for Documentation discrepancy (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Image generationvery low · 1K1$0.003image
Image generationvery low · 2K1$0.006image
Image generationlow · 1K1$0.0075image
Image generationlow · 2K1$0.015image
Image generationmedium · 1K1$0.01image
Image generationmedium · 2K1$0.02image
Image generationhigh · 1K1$0.015image
Image generationhigh · 2K1$0.03image
Image generationvery high · 1K1$0.02475image
Image generationvery high · 2K1$0.0495image

Rate conditions

  1. Replicate published billing tier, not native Pruna pricing. Very High request spelling is "very high"; billing criteria spelling is "very-high". Custom-dimension mapping not established.
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.

Ideogram API

Provider source (opens in a new tab)
API model ID
p-image-ideogram
Access
Hosted API; account and API key required. No generation was submitted.
Regions
Not established
API endpoint URL
POST https://api.ideogram.ai/v2/image/generate/p-image-ideogramSource for API endpoint URL (opens in a new tab)
Authentication
Api-Key header; application/json body with prompt at the top level.Source for Authentication (opens in a new tab)
Model controls
prompt, magic_prompt, seed, num_images, quality, resolution, aspect_ratio, custom_width, custom_height, enable_copyright_detection, async, webhook_urlSource for Model controls (opens in a new tab)
Required request fields
promptSource for Required request fields (opens in a new tab)
Maximum prompt characters
10,000Source for Maximum prompt characters (opens in a new tab)

Minimum 1 character. This limit belongs to Ideogram v2 and is not inherited by Pruna or Replicate.

Supported reasoning efforts
very_low, low, medium, high, very_highSource for Supported reasoning efforts (opens in a new tab)
Generation controls
quality defaults to medium; resolution defaults to 1k; num_images accepts 1–8, default 1.Source for Generation controls (opens in a new tab)
Aspect ratios
View all 15 entries
  • 1x3
  • 3x1
  • 1x2
  • 2x1
  • 9x16
  • 16x9
  • 10x16
  • 16x10
  • 2x3
  • 3x2
  • 3x4
  • 4x3
  • 4x5
  • 5x4
  • 1x1
Source for Aspect ratios (opens in a new tab)
Resolution controls
custom_width and custom_height must be provided together: each 16–4096 px, positive multiples of 16, combined area at most 4,194,304 px. Cannot combine custom sizes with resolution or aspect_ratio.Source for Resolution controls (opens in a new tab)
Prompt expansion
magic_prompt: auto, on or off; default auto.Source for Prompt expansion (opens in a new tab)
Seed control
Integer seed 0–2147483647.Source for Seed control (opens in a new tab)
Asynchronous generation
Synchronous by default. async=true or webhook_url returns a generation ID; poll GET /v2/generations/{generation_id}.Source for Asynchronous generation (opens in a new tab)
Request price quote
dry_run=true validates and quotes a request without generation or billing; API authentication is still required. No quote was requested.Source for Request price quote (opens in a new tab)
Pricing coverage
Not collected

Exact current Ideogram host tariff not recovered. The public product page gives approximate 1K figures; the dynamic pricing page did not expose its tariff in the capture. Do not copy Pruna or Replicate prices.

Content screening controls
Optional enable_copyright_detection adds checking. A flagged result can have is_image_safe=false and an empty image URL.Source for Content screening controls (opens in a new tab)

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.

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.

Pruna API

p-image-ideogram
Not verified

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

How it works
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Minimum reusable input
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Lifetime & refresh
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

How to enable it
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Usage fields
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Billing rules
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Limits & data boundaries
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

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

Caching reviewed 15 Oct 2026

Replicate

prunaai/p-image-ideogram
Not verified

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

How it works
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Minimum reusable input
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Lifetime & refresh
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

How to enable it
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Usage fields
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Billing rules
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Limits & data boundaries
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

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

Caching reviewed 15 Oct 2026

Ideogram API

p-image-ideogram
Not verified

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

How it works
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Minimum reusable input
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Lifetime & refresh
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

How to enable it
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Usage fields
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Billing rules
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

Limits & data boundaries
Not collected

No verified model prompt-cache contract or caching discount. Uploaded assets and asynchronous jobs are not prompt caching.

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

Caching reviewed 15 Oct 2026

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

Both Pruna and Ideogram identify this jointly developed hosted model. No matching checkpoint appears in the reviewed official inventories; Ideogram 4 public quantized weights are separately identified. Closed-weight classification is inferred, and shared JSON-prompt syntax does not establish equivalence to Ideogram 4 or a specific private architecture.

Classification evidence (opens in a new tab)

Sources reviewed