•

Open weights model

•

Released October 2026

Muse Spark Open (Xhigh) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Muse Spark Open (Xhigh) for your use-case.

Lowest Time per Task

#1
BasetenBaseten
3.8 min
#2
ModalModal
5.1 min
#3
FireworksFireworks
6.0 min
#4
Together AITogether AI
7.5 min
#5
Nebius (FP4)Nebius (FP4)
8.1 min

Time per Intelligence Index task (minutes)

Total 5 providers

Lowest Cost per Task

#1
ModalModal
$1.61
#2
Nebius (FP4)Nebius (FP4)
$1.61
#3
FireworksFireworks
$2.02
#4
Together AITogether AI
$2.02
#5
BasetenBaseten
$2.81

Cost per Intelligence Index task

Total 5 providers

Muse Spark Open (xhigh) is available through 5 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

  • For time per task, Baseten (3.8 min), Modal (5.1 min), and Fireworks (6.0 min) finish an Intelligence Index task fastest.
  • For cost per task, Modal ($1.61), Nebius (FP4) ($1.61), and Fireworks ($2.02) are the cheapest per Intelligence Index task.
Inference time (minutes) per Intelligence Index task · Lower is better
Weighted average cost (USD) per Intelligence Index task · Lower is better

Endpoint Accuracy

Endpoint Accuracy Index: Muse Spark Open (Xhigh)

v1.1 · Composite of BFCL v4-500, HLE-250 and AA-LCR-25 run against each provider endpoint · Percentage of the reference endpoint, with 95% confidence interval · Higher is better

Pricing

Cost per Intelligence Index Task: Muse Spark Open (Xhigh)

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Pricing: Cache Hit, Input, and Output: Muse Spark Open (Xhigh)

Price (USD per M Tokens) · Lower is better

Output Speed vs. Cost per Task: Muse Spark Open (Xhigh)

Output speed: output tokens divided by total request time, including time to first token · Weighted average cost (USD) per Intelligence Index task
Most attractive quadrant
Pareto line

Speed

Average of the single-request and multi-turn agentic workloads measured

Time per Intelligence Index Task: Muse Spark Open (Xhigh)

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Lower is better

Latency

Average of the single-request and multi-turn agentic workloads measured

Time to First Answer Token: Muse Spark Open (Xhigh)

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better

Reliability

Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

Endpoint Error Rate: Muse Spark Open (Xhigh)

Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better

Caching

Cache Hit Rate: Muse Spark Open (Xhigh)

Median across multi-turn agentic session runs in the last four weeks, updated Oct 26, 2026 · Higher is better

Cost per Task vs. Cache Hit Rate: Muse Spark Open (Xhigh)

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026
Most attractive quadrant

Key Comparison Metrics & API Features

Baseten logoBaseten
$2.81
4.8
94%
7.89
4.0%
1M
Open
Fireworks logoFireworks
$2.02
7.6
100%
11.85
0.0%
1M
Open
Modal logoModal
$1.61
6.9
95%
13.41
0.0%
1M
Open
Nebius logoNebius
$1.61
8.5
100%
14.58
1.4%
1M
Open
Together AI logoTogether AI
$2.02
7.9
100%
10.81
0.0%
1M
Open

Frequently Asked Questions

Common questions about Muse Spark Open (Xhigh) providers