Compute Screener
Updated 3:26 AM CST

Muse Ember API price per 1M tokens: input, cached and output prices, price chart and history

# Lab/Bloomberg ticker USD / 1M tokens 1D 1W 1M Trend Chart (3M)
1
StepFun
$0.2340.0%0.0%0.0%▲ Strong 6.1+80.5% a month
2
DeepSeek
$0.0274-1.1%-3.5%-6.5%▼ Strong 5.9-17.2% a month
3
AnthropicORNNTOKA
$0.636-6.6%+10.4%-3.9%▼ Strong 5.7-22.0% a month
4
Alibaba
$0.0717+19.1%+1.7%-14.2%▼ Strong 5.6-47.6% a month
5
Mistral
$0.1660.0%-9.1%+1.5%▲ Strong 4.7+130.2% a month
6
MiniMax
$0.0451-1.5%-1.3%-55.0%▼ Strong 4.5-27.4% a month
7
Google
$0.291+12.2%+19.5%+56.6%▲ Strong 4.3+26.7% a month
8
Moonshot AI
$0.570-3.3%-1.9%-26.0%▼ Moderate 3.8-9.7% a month
9
Xiaomi
$0.0295-0.3%-21.1%+6.1%▲ Moderate 3.3+20.5% a month
10
NVIDIA
$0.04040.0%0.0%-79.8%▼ Moderate 2.7-34.3% a month
11
Meta
$0.0167-0.6%+6.4%+6.4%▼ Weak 1.8-41.0% a month
12
OpenAIORNNTOKO
$0.122-10.7%-42.3%-31.0%▼ Weak 1.5-18.8% a month
13
Z.ai
$0.149-10.0%-10.5%-25.3%▼ Weak 1.4-13.3% a month
14
xAI
$0.7350.0%0.0%0.0%Weak 0.00.0% a month

Muse EmberMeta

$0.02050.0% (All)
USD / 1M tokens
Cache read $0.004 · Input $0.10 · Output $0.50 per 1M tokens, at 87% cache read, 12% input, 1% output
1D
1W
1M
3M
6M
YTD
1Y
0.0%
—
—
—
—
—
—
#ModelAs ofShareUSD / 1M tokens
1Muse Spark 1.3 ContributorNov 14, 7:57 PM CST79.9%$0.0157
2Muse EmberNov 14, 7:57 PM CST20.1%$0.0205

Break-even throughput by GPU

GPUUSD / GPU-hourTokens/s per GPU
B300$9.5713,291
B200$8.1411,302
H200$5.147,137
H100$3.745,190
RTX PRO 6000$2.142,977
A100$1.702,360
L40S$1.411,958
RTX 6000 Ada$0.941,300
L40$0.921,278
RTX 5090$0.70977
RTX A6000$0.60834
RTX 4090$0.53734

Gross margin calculator

Revenue—
GPU rental price$3.74
Gross profit—
Gross margin—

About Muse Ember

Muse Ember is a model from Meta. Its posted API price is $0.10 per 1M input tokens, $0.004 per 1M cached input tokens and $0.50 per 1M output tokens, or $0.0205 per 1M tokens at the mix of tokens agents send (87% cache read, 12% input, 1% output). Its price has not changed since Nov 10, 2026. It carries 20.1% of Meta's API tokens and is one of the 2 models in the Meta token price index, $0.0167 per 1M tokens today. Of the 32 models in the token index it is the 31st most expensive. At today's H100 rental price of $3.74 per GPU-hour, its break-even throughput is 5,190 tokens per second per GPU at its list price (3 input : 1 output). Prices are collected once a day, for each UTC day.

Models near this price

  • Qwen3.8 Flash (Alibaba): $0.0366 per 1M tokens at the mix, $0.15 input and $0.47 output
  • DeepSeek V4.1 Flash 1017 (DeepSeek): $0.0266 per 1M tokens at the mix, $0.15 input and $0.60 output
  • Claude Haiku 5.5 (Anthropic): $0.0257 per 1M tokens at the mix, $0.10 input and $0.50 output
  • GPT-6 Luna (OpenAI): $0.0257 per 1M tokens at the mix, $0.10 input and $0.50 output
  • MiMo-V2.6-Flash (Xiaomi): $0.0220 per 1M tokens at the mix, $0.14 input and $0.28 output
  • Muse Spark 1.3 Contributor (Meta): $0.0157 per 1M tokens at the mix, $0.10 input and $0.20 output

Cite as: Compute Screener, “Muse Ember API price”, computescreener.com/models/muse-ember. The figures are free to reuse under CC BY 4.0 with credit to Compute Screener.