Compare AI models

Specifications
Context window
1M1.05M
API pricing
Input price
$1.25$2.00
Output price
$4.25$10.00
Cached input price
$0.15$0.10
Cheapest input
$1.25Google$1.00OpenAI
Cheapest output
$4.25Google$5.00OpenAI
$463Meta list price$900OpenAI list price
Benchmarks
CheatBench
39%49.3%
DeepSWE 1.1
75.4%75.2%
Terminal-Bench 4.0
14.55%58.18%
OSWorld 2.0
66.9%71.4%
AutomationBench
49.6%36.2%
threejseval
14421972
Overview
CompanyMetaOpenAI
Release dateSep 2 2026Sep 29 2026
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Muse Spark 1.3 and GPT-6.1 Sol are evenly matched across the 6 benchmarks they both report. Muse Spark 1.3 is cheaper on both input and output: $1.25 vs $2.00 per million input tokens, and $4.25 vs $10.00 per million output tokens. Figures are base-tier rates. Muse Spark 1.3 shipped 27 days before GPT-6.1 Sol, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Muse Spark 1.3) vs 1.05M (GPT-6.1 Sol).

On CheatBench, Muse Spark 1.3 leads at 39% vs GPT-6.1 Sol at 49.3%. On DeepSWE 1.1, Muse Spark 1.3 leads at 75.4% vs GPT-6.1 Sol at 75.2%. On Terminal-Bench 4.0, GPT-6.1 Sol leads at 58.18% vs Muse Spark 1.3 at 14.55%. On OSWorld 2.0, GPT-6.1 Sol leads at 71.4% vs Muse Spark 1.3 at 66.9%. On AutomationBench, Muse Spark 1.3 leads at 49.6% vs GPT-6.1 Sol at 36.2%. On threejseval, GPT-6.1 Sol leads at 1972 vs Muse Spark 1.3 at 1442.