AiCostCompare

Muse Ember

by Meta · meta/muse-ember · #98 cheapest of 457 paid models

Prices updated Nov 18, 2026, 5:44 AM UTC · refreshed nightly

Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$0.10

per 1M tokens

Output

$0.50

per 1M tokens

Blended (3:1)

$0.20

3 input : 1 output

Cache read

$0.0040

per 1M cached tokens

Cache write

$0.125

per 1M tokens

Cache & batch economics

Effective prices for Muse Ember with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.20$0.0107—
50%$0.164$0.0059−45%
90%$0.135$0.00206−81%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.0002$0.2
Document summary8,0001,000$0.0013$1.30
Codebase question (RAG)30,0002,000$0.004$4.00
Long-context analysis150,0005,000$0.0175$17.50

Specs

Context window

1.05M

tokens

Max output

944K

tokens

Input modalities

text, image, video, file, audio

Tokenizer

Other