Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Meta / Muse Image

Muse Image

Image generation and editing with reference images, conversational refinement and internal search/code tools. Billed per returned image.

Image generation
availableClosed weightsImage generationImage editing
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
11 of 21 specification fields collected
Output resolutionsize selects aspect ratio, not exact output pixels; ratios over 16:1 are rejectedSee specification notes below
Reference images1–10 images per editSee specification notes below
Input billingSee ratesMeta Model 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)

reasoning_strength controls generation refinement; this is not the text-model reasoning-effort contract.

Tool calling
Not supportedSource for Tool calling (opens in a new tab)

Customer function tools and separate web_search tools are rejected. The model can internally use search and code while generating images.

Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)

SSE emits a completed image, not partial-image previews.

Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2026-07-07Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected
Output formats
WEBP, PNG, JPEGSource for Output formats (opens in a new tab)
Reference images
1–10 images per editSource for Reference images (opens in a new tab)
Output resolutions
size selects aspect ratio, not exact output pixels; ratios over 16:1 are rejectedSource for Output resolutions (opens in a new tab)
internalTools
Built-in reference search, fact search and layout code executionSource for internalTools (opens in a new tab)
watermarking
Content Seal watermark on Meta AI app/web image outputsSource for watermarking (opens in a new tab)

The research release does not establish identical watermark guarantees for every API output.

Access & pricing

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

Meta Model API

Provider source (opens in a new tab)
API model ID
muse-image-1.0
Access
Bearer-authenticated POST https://api.meta.ai/v1/images/generations. Single-shot text-to-image generation.
Regions
Availability is geography-controlled; see Meta geographic-use policy. No data-residency guarantee is inferred. Muse Image is restricted in India under the current geographic-use policy.
responseFormats
Base64 JSON (default) or temporary signed URLSource for responseFormats (opens in a new tab)
reasoningLevels
low, highSource for reasoningLevels (opens in a new tab)

high is default; price per image is unchanged.

Request quotas
150 requests/minute per team; no token-per-minute quotaSource for Request quotas (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Image generationGenerated image1$0.01image

Rate conditions

  1. Only successfully generated and returned images are billed; failed or safety-filtered images are excluded. Multiple returned images are charged individually. Internal tools and refinement are included.
Pricing source (opens in a new tab)

Data & enterprise terms

Standard requests are not used to train Meta models. Terms allow retention for service operation, safety/security, legal and policy purposes without a fixed general duration. Standard mode is not itself a zero-retention guarantee.

Read the service policy (opens in a new tab)

Meta Model API

Provider source (opens in a new tab)
API model ID
muse-image-1.0
Access
Bearer-authenticated POST https://api.meta.ai/v1/images/edits. Reference images by file_id or image_url; JSON or multipart upload.
Regions
Availability is geography-controlled; see Meta geographic-use policy. No data-residency guarantee is inferred. Muse Image is restricted in India under the current geographic-use policy.
responseFormats
Base64 JSON (default) or temporary signed URLSource for responseFormats (opens in a new tab)
reasoningLevels
low, highSource for reasoningLevels (opens in a new tab)

high is default; price per image is unchanged.

Request quotas
150 requests/minute per team; no token-per-minute quotaSource for Request quotas (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Image generationGenerated image1$0.01image

Rate conditions

  1. Only successfully generated and returned images are billed; failed or safety-filtered images are excluded. Multiple returned images are charged individually. Internal tools and refinement are included.
Pricing source (opens in a new tab)

Data & enterprise terms

Standard requests are not used to train Meta models. Terms allow retention for service operation, safety/security, legal and policy purposes without a fixed general duration. Standard mode is not itself a zero-retention guarantee.

Read the service policy (opens in a new tab)

Meta Model API

Provider source (opens in a new tab)
API model ID
muse-image-1.0
Access
Bearer-authenticated POST https://api.meta.ai/v1/responses. Conversational editing via Responses.
Regions
Availability is geography-controlled; see Meta geographic-use policy. No data-residency guarantee is inferred. Muse Image is restricted in India under the current geographic-use policy.
responseFormats
Responses output includes generated image dataSource for responseFormats (opens in a new tab)
reasoningLevels
low, highSource for reasoningLevels (opens in a new tab)

high is default; price per image is unchanged.

Request quotas
150 requests/minute per team; no token-per-minute quotaSource for Request quotas (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Image generationGenerated image1$0.01image

Rate conditions

  1. Only successfully generated and returned images are billed; failed or safety-filtered images are excluded. Multiple returned images are charged individually. Internal tools and refinement are included.
Pricing source (opens in a new tab)

Data & enterprise terms

Standard requests are not used to train Meta models. Terms allow retention for service operation, safety/security, legal and policy purposes without a fixed general duration. Standard mode is not itself a zero-retention guarantee.

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.

Meta Model API

muse-image-1.0
Not verified

No endpoint-specific discounted prompt-cache contract verified.

How it works
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Minimum reusable input
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Lifetime & refresh
Not collected

No endpoint-specific discounted prompt-cache contract verified.

How to enable it
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Usage fields
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Billing rules
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Limits & data boundaries
Not collected

No endpoint-specific discounted prompt-cache contract verified.

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

Meta Model API

muse-image-1.0
Not verified

No endpoint-specific discounted prompt-cache contract verified.

How it works
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Minimum reusable input
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Lifetime & refresh
Not collected

No endpoint-specific discounted prompt-cache contract verified.

How to enable it
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Usage fields
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Billing rules
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Limits & data boundaries
Not collected

No endpoint-specific discounted prompt-cache contract verified.

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

Meta Model API

muse-image-1.0
Not verified

No endpoint-specific discounted prompt-cache contract verified.

How it works
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Minimum reusable input
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Lifetime & refresh
Not collected

No endpoint-specific discounted prompt-cache contract verified.

How to enable it
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Usage fields
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Billing rules
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Limits & data boundaries
Not collected

No endpoint-specific discounted prompt-cache contract verified.

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

Meta identifies this native Muse model in its research or hosted-model catalog. The reviewed release is available through provider-controlled service, subscription or research preview, without a released weight artifact in the reviewed inventory. The September Spark roadmap still describes its weight release as forthcoming. Open-weight Glimmer, SAM and Llama are excluded separately; hosted access alone does not turn those models into closed models.

Classification evidence (opens in a new tab)

Lifecycle dates

Provider release7 Jul 2026Source (opens in a new tab)

Sources reviewed