Published token rates
| Tier | Input / 1M | Output / 1M | Cached input / 1M |
|---|---|---|---|
| Standard | $1.25 | $4.25 | $0.15 |
| Contributor | $0.10 | $0.20 | $0.002 |
Contributor tier trade-off
Contributor input is 12.5 times cheaper than standard input, and output is 21.25 times cheaper. In exchange, prompts may be used to improve Meta products. The standard endpoint keeps customer data private and out of training.
Ready to test the workflow?
Create account & add creditsPrice did not change from 1.2
Muse Spark 1.3 kept the same standard $1.25 input and $4.25 output rates as Muse Spark 1.2.
Frequently asked questions
Can I run Muse Spark 1.3 on OneInfer?
No. As of 3 September 2026, Muse Spark 1.3 is proprietary, has no downloadable weights, and resolves to Meta as its single upstream provider. OneInfer publishes this independent reference without claiming deployment availability.
How much does Muse Spark 1.3 cost?
Standard list pricing is $1.25 per million input tokens, $4.25 per million output tokens and $0.15 per million cached input tokens.
What is the Muse Spark Contributor tier?
It is a lower-cost endpoint priced at $0.10 input and $0.20 output per million tokens; prompts may be used to improve Meta products.
Put Muse Spark 1.3 to work
Fund a controlled evaluation, send a reference frame or document, and measure quality and cost on your own workload.