Muse Spark 1.3 Providers: One Upstream, Three Routes

Muse Spark 1.3 lists at $1.25 input and $4.25 output per 1M tokens on Meta’s first-party route. Meta Model API, Muse Code CLI and ModelsLab all expose the same upstream checkpoint, so the route count is three but the inference backend count is one. OneInfer also serves it through Meta; the live OneInfer price is in the table below.

Create account & add creditsGet API Key

Last verified 3 September 2026.

Use Muse Spark 1.3 in 4 steps

Step 1 of 4

Try Muse Spark 1.3 in the OneInfer playground without writing code, or create an API key in the Console to call it from your app.

export ONEINFER_API_KEY="your-api-key"

Tracked providers

ProviderInput /1M tokensOutput /1M tokensProvenance
Meta$1.250$4.250vendor reported

What is Muse Spark 1.3?

Muse Spark 1.3 is Meta's closed-weight multimodal agentic model released on 2 September 2026. It accepts text, image, audio and video, returns text, and resolves to Meta as its single upstream owner because no other party can independently deploy the weights.

Ready to test the workflow?

Create account & add credits

Why route count is not provider diversity

Because weights are closed, no route can independently deploy the checkpoint. Outages, policy changes and model updates therefore retain a common Meta dependency.

Frequently asked questions

Can I run Muse Spark 1.3 on OneInfer?

Yes. Muse Spark 1.3 is available on OneInfer with the model ID meta/muse-spark-1.3. Meta has not released the weights, so it can be called through the API but not self-hosted.

How many Muse Spark 1.3 providers are there?

There are four verified access routes, but they all resolve to one upstream model owner: Meta.

Put Muse Spark 1.3 to work

Fund a controlled evaluation, test it on your own inputs, and measure quality and cost on your workload.

Create account & add creditsRun this with Muse Spark 1.3