modelbenchmark.io

Muse Ember 1.0

Meta · muse-ember-1-0

Compare

Muse Ember is Meta's smallest and most efficient reasoning model, built for the work agents repeat all day: tool calls, coding subtasks, routing, extraction, and long-document parsing. It pairs with Muse Wonder or Muse Spark, which plan while Muse Ember handles the volume.

Specification

most-agreed values

Context
1M
Max output
524K
Released
2026-11-09
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image, video, pdf, audio
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.10
Output
$0.50
Cache read
$0.004
Cache write
free

Long-context price tiers

the rate above each context threshold

AbovePrice$/M
200KCache read$0.012
200KInput$0.30
200KOutput$1.50

Available from 5 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
cloudflare-ai-gateway$0.10$0.50$0.004—1M524K—
llmgateway$0.10$0.50$0.004—1M524K—
llmgateway-providers$0.10$0.50$0.004—1M524K—
meta$0.10$0.50$0.004—1M524K—
opencode$0.10$0.50$0.004free1M270K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-11-10metaCache read$0.004
2026-11-11metaCache read$0.004
2026-11-10metaInput$0.10
2026-11-11metaInput$0.10
2026-11-10metaOutput$0.50
2026-11-11metaOutput$0.50

More from Meta

most-hosted first