Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Leonardo AI / Phoenix

Phoenix 1.0

Phoenix 1.0 generates images from text with reference-image guidance and selectable quality modes.

Image generation
availableClosed weightsImage generation
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
13 of 28 specification fields collected
Text input limit2K2,000
Maximum outputNot collectedAwaiting source review
Input billingSee billing notesLeonardo AI API
Output billingSee billing notesAccess and billing notes 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 named model. API transport and training features are not inferred from platform-level marketing.

Maximum input tokens
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Maximum output
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Reasoning
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Tool calling
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Structured output
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Streaming
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Batch processing
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Fine-tuning
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Knowledge cutoff
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Release date
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Parameters
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Architecture
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Languages
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Context caching
Not collected

Not established for this named model. API transport and training features are not inferred from platform-level marketing.

Input modalities
Text, ImageSource for Input modalities (opens in a new tab)
Output modalities
ImageSource for Output modalities (opens in a new tab)
Prompt length limit
1–2000 charactersSource for Prompt length limit (opens in a new tab)

Native v2 request limit; characters are not language tokens.

Maximum prompt characters
2,000Source for Maximum prompt characters (opens in a new tab)

Native v2 text prompt limit. Reference images are separate inputs.

Published price
Configuration-based USD pricing; use the Leonardo API calculator for an exact quote.Source for Published price (opens in a new tab)
Random seed
Non-negative integer; upper bound not specified.Source for Random seed (opens in a new tab)
Prompt expansion
AUTO, ON or OFF; AUTO by default.Source for Prompt expansion (opens in a new tab)
Images per request
8Source for Images per request (opens in a new tab)

Default 4; multiple images in one generation are not a discounted Batch API.

Supported image sizes
Width 32–2048px; height 32–2048px; multiples of 8. Default 1024×1024.Source for Supported image sizes (opens in a new tab)

Request dimensions, not an unconditional final pixel ceiling after quality processing.

Generation modes
FAST, QUALITY, ULTRASource for Generation modes (opens in a new tab)

Default FAST. Quality modes are options on the same model, not separate model records.

Reference guidance
Style: up to 4 images; content, character and image-to-image: up to 1 each.Source for Reference guidance (opens in a new tab)

UPLOADED or GENERATED image IDs; each guidance type has its own strength options.

Model aliases
de7d3faf-762f-48e0-b3b7-9d0ac3a3fcf3Source for Model aliases (opens in a new tab)

Legacy API UUID. The v2 model selector is recorded on the native endpoint; these are not extra models.

Negative prompt support
Up to 1000 characters; optional tiling.Source for Negative prompt support (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.

Leonardo AI API

Provider source (opens in a new tab)
API model ID
phoenix-v1.0
Access
Bearer API key and funded API account. Documentation reviewed; no inference request sent.
Regions
Not established
API endpoint URL
POST https://cloud.leonardo.ai/api/rest/v2/generationsSource for API endpoint URL (opens in a new tab)
Processing workflow
Asynchronous generation submission returns generationId for result retrieval. Not token streaming.Source for Processing workflow (opens in a new tab)
Billing basis
PAYG account balance in US dollars; configuration-specific generation charges.Source for Billing basis (opens in a new tab)
Pricing coverage
Use the authenticated API pricing calculator for the exact configuration. Responses report cost amount and unit; apiCreditCost remains during migration.Source for Pricing coverage (opens in a new tab)

The captured generic OpenAPI response only lists generationId and apiCreditCost; the newer FAQ describes the cost object.

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

Data & enterprise terms

public controls community-feed visibility. Setting false is not evidence of zero retention or a no-training policy.

Read the service policy (opens in a new tab)

Replicate

Provider source (opens in a new tab)
API model ID
leonardoai/phoenix-1.0
Access
Replicate hosted prediction API; account and billing required. No inference request sent.
Regions
Not established
Hosted API version
e4f414227cdf53a79e9b26daac28f24c09567ad5c3c0ee803b128b3bd55a7c11Source for Hosted API version (opens in a new tab)

Replicate wrapper version, not a named model release date.

API endpoint URL
POST https://api.replicate.com/v1/models/leonardoai/phoenix-1.0/predictionsSource for API endpoint URL (opens in a new tab)
Aspect ratios
View all 13 entries
  • 1:1
  • 16:9
  • 9:16
  • 3:2
  • 2:3
  • 4:5
  • 5:4
  • 3:4
  • 4:3
  • 2:1
  • 1:2
  • 3:1
  • 1:3
Source for Aspect ratios (opens in a new tab)
Pricing coverage
USD 1.50 per 1,000 metered units. README examples: 12/25/50 units for one fast/quality/ultra image; 21/77/173 for four; 33/153/337 for eight. Displayed example dollar amounts are rounded. These units are not language tokens.Source for Pricing coverage (opens in a new tab)

Examples do not establish an exact tariff for every resolution and option.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Hosted generationunit1$1.501,000 metered units

Rate conditions

  1. Host tariff per 1,000 units, not per image or token. Configuration-dependent unit consumption; see published examples in endpoint details.
Pricing source (opens in a new tab)

Data & enterprise terms

Model page states that input data is forwarded to Leonardo Interactive Pty Ltd.

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.

Leonardo AI API

phoenix-v1.0
Not verified

No prompt-cache API contract or discount established for this endpoint.

How it works
Not collected

No prompt-cache API contract or discount established for this endpoint.

Minimum reusable input
Not collected

No prompt-cache API contract or discount established for this endpoint.

Lifetime & refresh
Not collected

No prompt-cache API contract or discount established for this endpoint.

How to enable it
Not collected

No prompt-cache API contract or discount established for this endpoint.

Usage fields
Not collected

No prompt-cache API contract or discount established for this endpoint.

Billing rules
Not collected

No prompt-cache API contract or discount established for this endpoint.

Limits & data boundaries
Not collected

No prompt-cache API contract or discount established for this endpoint.

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

Caching reviewed 15 Oct 2026

Replicate

leonardoai/phoenix-1.0
Not verified

No prompt-cache API contract or discount established for this endpoint.

How it works
Not collected

No prompt-cache API contract or discount established for this endpoint.

Minimum reusable input
Not collected

No prompt-cache API contract or discount established for this endpoint.

Lifetime & refresh
Not collected

No prompt-cache API contract or discount established for this endpoint.

How to enable it
Not collected

No prompt-cache API contract or discount established for this endpoint.

Usage fields
Not collected

No prompt-cache API contract or discount established for this endpoint.

Billing rules
Not collected

No prompt-cache API contract or discount established for this endpoint.

Limits & data boundaries
Not collected

No prompt-cache API contract or discount established for this endpoint.

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

The native model schema explicitly identifies the Phoenix and Lucid generation modes as proprietary. Access is through hosted generation APIs; no checkpoint download or open-weight license is established by the reviewed sources.

Classification evidence (opens in a new tab)

Sources reviewed