Phaseo

Muse Ember 1.0 vs Muse Spark 1.3

Pick a route and service tier under each model. Prices, the calculator and the verdicts follow your choice.

Try Muse Ember 1.0 in Chat
Muse Ember 1.0
Muse Spark 1.3

At a glance

Generated from the rows below

Choose Muse Ember 1.0 for

  • The lowest cost per typical request ($0.0005)
  • The longest output: 524,288 tokens

Choose Muse Spark 1.3 for

  • The most routes on Phaseo: 2

Overview

Lab
Meta
Meta
Context window
1.05Mtokensfrom provider listings
1.05Mtokens
Max output
524Ktokens (best)from provider listings
131Ktokensfrom provider listings
Takes
Text, Image, Video, Audio
Text, Image, Video, Audio
Returns
Text
Text
Routes on Phaseo
1 provider
2 providers
 (best)
Released
9 Nov 2026
2 Sept 2026

Pricing

Prices on the route and tier chosen under each model

Meta · StandardMeta · Standard
Input
from $0.10/ 1M tokensInput ≤ 200K$0.10Input > 200K$0.30
$1.25/ 1M tokens
Output
from $0.50/ 1M tokensInput ≤ 200K$0.50Input > 200K$1.50
$4.25/ 1M tokens
Cache read
from $0.004/ 1M tokensInput ≤ 200K$0.004Input > 200K$0.012
$0.15/ 1M tokens
Typical request2K tokens in, 500 out
$0.0005 (best)
$0.0046

What will it cost?

Estimate a month of requests on the route and tier chosen for each model

ModelPer requestPer month
Muse Ember 1.0Meta · Standard$0.0005$13.50
Muse Spark 1.3Meta · Standard$0.0046$138.75

Uses the route and tier chosen under each model, over 30 days. Cached input is billed at the cache-read rate.

Performance

Live gateway traffic

Latency p50last 24 hours
1.64 s
No traffic in the last 5 days
Throughput p50last 24 hours
111 tps
No traffic in the last 5 days
Requests, last 24 hours
1
None in the last 24 hours

Activity

Tokens sent through Phaseo each day over the last 30 days

Tokens, last 30 days
841
No traffic through Phaseo in the last 30 days
Per day
841
12 Oct10 Nov
Input
646
–
Output
18
–
Reasoning
177
–
Requests
1
–

Features

Features from the parameters Phaseo routes support

Tool calling
Yes
Yes
Structured outputs
Yes
Yes
Reasoning effort
Yes
Yes
Web search
Yes
Yes
Prompt cachingon the chosen route
Yes
Yes
Quantisationon the chosen route
Not stated
Not stated

Benchmarks

Only results that two or more of the selected models report get a row

Compare at effort

Artificial Analysis Intelligence Index Independent

Higher is better · at Max effort · 2 of 2 models tested

Muse Ember 1.036
Muse Spark 1.336.6

Where they rank

The five leaders on each capability index, then the compared models. Each model at its best-scoring setting.

Artificial Analysis Intelligence Index58 models ranked

  1. #1Claude Fable 5.264.6
  2. #2Claude Opus 5.559.1
  3. #3GPT-6 Astra56.9
  4. #4GPT-6.1 Sol54.6
  5. #5Claude Sonnet 5.554.5
  6. #14Muse Spark 1.336.6
  7. #16Muse Ember 1.036.0

Artificial Analysis Coding Index171 models ranked

  1. #1Claude Fable 5.181.6
  2. #2GPT 5.6 Sol78.3
  3. #3Claude Opus 578.0
  4. #4GPT-6 Astra77.1
  5. #5Grok 4.676.8
  6. #7Muse Spark 1.376.5

Artificial Analysis Agentic Index112 models ranked

  1. #1Claude Fable 5.157.9
  2. #2Claude Opus 556.5
  3. #3Qwen 3.8 Max 090256.0
  4. #4Muse Spark 1.355.5
  5. #5Qwen 3.8 Flash Next53.6

Epoch Capabilities Index166 models ranked

  1. #1Claude Fable 5.2174.2
  2. #2GPT-6 Astra169.2
  3. #3GPT-6.1 Sol168.9
  4. #4Claude Opus 5.5168.7
  5. #5GPT-6.1 Terra168.1
  6. #24Muse Spark 1.3158.0
Cost
Artificial Analysis Evaluation Cost (USD)matched by effort level · lower is better
$117.12 (best)
$1,906

Lab-reported results come from each lab’s own launch materials and may use different settings, so none is marked best. Independent results come from third-party evaluators.

Providers

Where each model runs on Phaseo, with standard-tier prices per 1M tokens. Providers that serve more of these models come first.

Meta
$0.10 in · $0.50 out (best)from $2.50 per 1K requests Native web search requests1.05M context
$1.25 in · $4.25 out$2.50 per 1K requests Native web search requests1.05M context
EmpirioLabs AI
—
$1.25 in · $4.25 out1.05M context

To price the whole page on one of these providers, pick it under the model’s name at the top.

Details

Knowledge cutoff
Not published
Not published
Status
Available
Available
Licence
Proprietary
Proprietary
Subscription plans
None mapped
6 plansCursor Enterprise, Cursor Pro, Cursor Pro+…
API docs
Not published
Open docs

Muse Ember 1.0 vs Muse Spark 1.3: side-by-side summary

Muse Ember 1.0 and Muse Spark 1.3 are both available through the Phaseo API, so switching between them is a change of model id rather than a new integration.

Muse Ember 1.0 is from Meta. It has a 1,048,576-token context window. On its cheapest route it costs $0.10 per 1M input tokens and $0.50 per 1M output tokens.

Muse Spark 1.3 is from Meta. It has a 1,048,576-token context window. On its cheapest route it costs $1.25 per 1M input tokens and $4.25 per 1M output tokens.

Muse Ember 1.0 model details, providers and pricingMuse Spark 1.3 model details, providers and pricing

Muse Ember 1.0 vs Muse Spark 1.3 at a glance

Muse Ember 1.0 and Muse Spark 1.3 compared on price, context window and benchmark score
AttributeMuse Ember 1.0Muse Spark 1.3
LabMetaMeta
Input price per 1M tokens$0.10$1.25
Output price per 1M tokens$0.50$4.25
Context window1,048,576 tokens1,048,576 tokens
Max output524,288 tokens131,072 tokens
Artificial Analysis Intelligence Index36.0 (#16)36.6 (#14)

Prices are each model's cheapest standard route on Phaseo. Benchmark ranks use each model's best-scoring evaluated setting.

Frequently asked questions

Which is cheaper, Muse Ember 1.0 or Muse Spark 1.3?

Muse Ember 1.0 is cheaper for both input and output tokens. Muse Ember 1.0 costs $0.10 per 1M input tokens and $0.50 per 1M output tokens; Muse Spark 1.3 costs $1.25 and $4.25, each on its cheapest standard route on Phaseo.

Which has the longer context window, Muse Ember 1.0 or Muse Spark 1.3?

Both have a 1,048,576-token context window.

Which scores higher on the Artificial Analysis Intelligence Index, Muse Ember 1.0 or Muse Spark 1.3?

Muse Spark 1.3 scores higher on the Artificial Analysis Intelligence Index. Muse Spark 1.3 scores 36.6, ranked #14 of 58. Muse Ember 1.0 scores 36.0, ranked #16 of 58.

Can I use Muse Ember 1.0 and Muse Spark 1.3 through one API?

Yes. Both are served through the Phaseo API, so you can switch between them by changing the model id.

Help keep public data accurate

See something missing, incorrect, or out of date? Tell us about this page.