Meta / meta/muse-image-1.0

Muse Image - access through LLMTR

Muse Image is Meta's text-to-image generation model. Before it renders, it can look things up in the real world: it pulls visual references for a known landmark, product, logo, or style, looks up current facts for a request that depends on real-world information (a price, a date, a result), and works out element layout for structured graphics such as infographics or charts. This lookup step is automatic, needs no configuration, and is included in the flat per-image price. You can request more than one image in a single call (the n parameter), and choose the output format (PNG, JPEG, or WebP) and the return shape (base64 or a temporary URL). Billing is a flat rate per image that is actually generated and returned; images that fail to generate or are removed by safety filtering are not charged.

Technical specifications

Canonical IDmeta/muse-image-1.0
ProviderMeta
Context windowNot available
OperationsIMAGES_GENERATIONS
Modalitiesimage, text

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
IMAGES_GENERATIONSOUTPUT_IMAGEPER_IMAGE$0.010000

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"meta/muse-image-1.0","messages":[{"role":"user","content":"Hello"}]}'

Related models