Muse Spark Open vs MiniMax M3

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

Muse Spark Open
MiniMax M3

At a glance

Generated from the rows below

Choose Muse Spark Open for

  • The highest Epoch Capabilities Index (155.1)
  • The largest context window: 1,048,576 tokens
  • The only one that takes audio

Choose MiniMax M3 for

  • The lowest cost per typical request ($0.0009)

Overview

Context window
1.05Mtokens (best)
1Mtokens
Max output
Not published
1.05Mtokensfrom provider listings
Takes
Text, Images, Video, Audio
Text, Images, Video
Returns
Text
Text
Routes on Phaseo
None
13 providers
Released
15 Oct 2026
1 Jun 2026

Pricing

Prices on the route and tier chosen under each model

Baseten listing, not routed by Phaseo · StandardCoreWeave Forge · Standard
Input
$1.25/ 1M tokens
$0.23/ 1M tokens (best)
Output
$4.25/ 1M tokens
$0.96/ 1M tokens (best)
Cache read
$0.15/ 1M tokens
$0.05/ 1M tokens (best)
Typical request2K tokens in, 500 out
$0.0046
$0.0009 (best)

What will it cost?

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

ModelPer requestPer month
Muse Spark OpenBaseten · Standard$0.0046$138.75
MiniMax M3CoreWeave Forge · Standard$0.0009$28.20

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 p50
No traffic yet
No traffic yet
Throughput p50
No traffic yet
No traffic yet
Requests, last 24 hours
No traffic yet
No traffic yet

Activity

Tokens sent through Phaseo each day over the last 30 days

None of these models has had traffic through Phaseo in the last 30 days.

Features

Features from the parameters Phaseo routes support

Tool calling
No route data
Yes
Structured outputs
No route data
Yes
Reasoning effort
No route data
Yes
Web search
No route data
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

Epoch Capabilities Index Independent

Higher is better · dot is the estimate, band is the 95% confidence interval · Epoch AI, CC BY 4.0

Muse Spark Open155.1 95% CI 153.1–157.3
MiniMax M3146.9 95% CI 142.4–150.3

Artificial Analysis Intelligence Index Independent

Higher is better · at Extra high effort · 1 of 2 models tested

Muse Spark Open38.9
MiniMax M329.2

Where they rank

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

Artificial Analysis Intelligence Index42 models ranked

  1. #1Claude Opus 5.558.4
  2. #2GPT-6 Astra56.9
  3. #3GPT-6.1 Sol54.5
  4. #4Claude Sonnet 5.554.2
  5. #5GPT-6.1 Terra51.0
  6. #27Muse Spark Open24.7
  7. #30MiniMax M318.7

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. #44MiniMax M358.6

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
  6. #31MiniMax M329.5

Epoch Capabilities Index164 models ranked

  1. #1GPT-6 Astra169.1
  2. #2Claude Opus 5.5168.4
  3. #3GPT-6.1 Terra168.1
  4. #4GPT-6.1 Sol167.8
  5. #5Claude Sonnet 5.5166.7
  6. #38Muse Spark Open155.1
  7. #71MiniMax M3146.9
Cost
Artificial Analysis Evaluation Cost (USD)matched by effort level · lower is better
$1,185
$537.98 (best)
Artificial Analysis Evaluation Cost (USD)matched by effort level · lower is better
$1,697
$878.03 (best)
General
24.7 (best)
18.7
306.7 (best)
290.9

Lab-reported results come from each lab’s own launch materials and may use different settings. Independent results come from third-party evaluators.

Providers

Routes Phaseo serves today, standard-tier prices per 1M tokens

Phaseo doesn’t route Muse Spark Open today.

Also listed, not routed by Phaseo: 9 providers

AI/ML API, Baseten, Doubleword, Fireworks, Groq, Modal, Nebius Token Factory, Together, Vercel AI Gateway

Shown for reference: other gateways’ listings and routes Phaseo has retired or disabled.

Details

Knowledge cutoff
Not published
Not published
Status
Available
Available
Licence
Muse Model License
MiniMax Community License
Subscription plans
None mapped
3 plansMiniMax Token Plan Max, MiniMax Token Plan Plus, MiniMax Token Plan Ultra
API docs
Not published

Muse Spark Open vs MiniMax M3: side-by-side summary

Muse Spark Open 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.

MiniMax M3 is from MiniMax. It has a 1,000,000-token context window. On its cheapest route it costs $0.23 per 1M input tokens and $0.96 per 1M output tokens.

Muse Spark Open model details, providers and pricingMiniMax M3 model details, providers and pricing

Muse Spark Open vs MiniMax M3 at a glance

Muse Spark Open and MiniMax M3 compared on price, context window and benchmark score
AttributeMuse Spark OpenMiniMax M3
LabMetaMiniMax
Input price per 1M tokens$1.25$0.23
Output price per 1M tokens$4.25$0.96
Context window1,048,576 tokens1,000,000 tokens
Max outputNot listed1,048,576 tokens
Artificial Analysis Intelligence Index24.7 (#27)18.7 (#30)

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 Spark Open or MiniMax M3?

MiniMax M3 is cheaper for both input and output tokens. Muse Spark Open costs $1.25 per 1M input tokens and $4.25 per 1M output tokens; MiniMax M3 costs $0.23 and $0.96, each on its cheapest standard route on Phaseo.

Which has the longer context window, Muse Spark Open or MiniMax M3?

Muse Spark Open has the longer context window at 1,048,576 tokens, compared with 1,000,000 tokens for MiniMax M3.

Which scores higher on the Artificial Analysis Intelligence Index, Muse Spark Open or MiniMax M3?

Muse Spark Open scores higher on the Artificial Analysis Intelligence Index. Muse Spark Open scores 24.7, ranked #27 of 42. MiniMax M3 scores 18.7, ranked #30 of 42.

Help keep public data accurate

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