Muse Spark 1.2

meta/muse-spark-1.2

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...

InputAudioFileImageTextVideo
OutputText
Input / Outputclub$1.325 / $4.505per 1M tokens · USD
Context window1Mtoken
Maximum output943.7Ktoken

Pricing

Current model usage rates. Choose your plan to see its published prices.

Pricing
UsagePricing
InputUS$1.325/ 1M token
Cache readUS$0.159/ 1M token
OutputUS$4.505/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
AudioFileImageTextVideo
Output
Text
Context window
1,048,576 token
Maximum output
943,718 token
Reasoning
xhigh · high · medium · low · minimal

Providers

Model supply available through Vecbase.

Via OpenRouter

Access is subject to your account’s permissions and model availability.

Frequently asked questions

What is Muse Spark 1.2, and who develops it?

Muse Spark 1.2 is a model from meta. Its model ID on Vecbase is meta/muse-spark-1.2. Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...

How much does Muse Spark 1.2 cost on Vecbase?

For Muse Spark 1.2, the Club plan lists USD 1.325 per 1 million input tokens and USD 4.505 per 1 million output tokens, as of 10/22/2026, 9:26:00 PM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.

How many tokens fit in Muse Spark 1.2’s context window?

Muse Spark 1.2 has a context window of 1,048,576 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for Muse Spark 1.2?

Muse Spark 1.2 can generate up to 943,718 tokens per response. Your API or request settings may set a lower limit.

Can Muse Spark 1.2 call tools in an agent workflow?

Yes. Muse Spark 1.2 supports tool calling. Your application provides the tool definitions and runs the tools the model requests.

Does Muse Spark 1.2 support structured outputs?

Yes. Muse Spark 1.2 supports structured output. Set the required format in your API request and check the returned data before using it.

Which input and output formats does Muse Spark 1.2 support?

Muse Spark 1.2 accepts Audio, File, Image, Text, and Video and produces Text.

Which providers make Muse Spark 1.2 available through Vecbase?

Vecbase offers Muse Spark 1.2 through OpenRouter. Availability may vary by provider.

Which model ID should an agent use to request Muse Spark 1.2?

Use meta/muse-spark-1.2 as the model identifier for Muse Spark 1.2. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

Which reasoning settings are listed for Muse Spark 1.2?

Muse Spark 1.2 supports these reasoning levels: xhigh, high, medium, low, and minimal. Available options depend on your API.

What does an agent need to access Muse Spark 1.2 through Vecbase?

To use Muse Spark 1.2, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.

Is a release date available for Muse Spark 1.2?

We do not yet have a confirmed release date for Muse Spark 1.2.

Which models can I compare with Muse Spark 1.2 on Vecbase?

You can compare Muse Spark 1.2 with Muse Spark 1.1 (meta/muse-spark-1.1), Muse Spark 1.2 Contributor (meta/muse-spark-1.2-contributor), and Muse Spark 1.3 Contributor (meta/muse-spark-1.3-contributor). Check their capabilities and prices to find the best fit for your task.