By meta · Updated 2026-11-01 · Reads imageslong-context / RAGreads images / documentsaudiostep-by-step reasoning
Meta: Muse Wonder is best suited for long-context / RAG, reads images / documents, audio, step-by-step reasoning. Access it through one Appmo API key alongside 444 other models — Appmo's optimizer can route to it automatically when it is the best value for a request.
Not enough posts yet to judge community sentiment. 6 Hacker News stories (682 points) · 69 new GitHub repos mentioning it. How we measure this.
curl https://appmo.com/v1/chat/completions \
-H "Authorization: Bearer $APPMO_KEY" \
-d '{"model":"meta/muse-wonder","messages":[{"role":"user","content":"Hello"}]}'How much does Meta: Muse Wonder cost?
Meta: Muse Wonder costs $4 per 1M input tokens and $20 per 1M output tokens ($8 blended), as of 2026-11-01. Prices are expected to fall as competition increases.
What is Meta: Muse Wonder best for?
Meta: Muse Wonder is best suited for long-context / RAG, reads images / documents, audio, step-by-step reasoning.
How do I use Meta: Muse Wonder?
Send requests to Appmo's OpenAI-compatible endpoint with model id "meta/muse-wonder" and one API key — no separate provider account needed.
Is Meta: Muse Wonder open source?
We have no record of public weights for Meta: Muse Wonder; treat it as a closed model available only through its provider's API.
Can Meta: Muse Wonder create images?
No. Meta: Muse Wonder can read and understand images, but it only writes text.