We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Meta: Muse Spark 1.2
meta/muse-spark-1.2Try Meta: Muse Spark 1.2 now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
Meta: Muse Spark 1.2 at a glance
- Input price is 178% higher than the median of 434 Text models.
- Context window of 1,048,576 tokens, enough for long documents and multi-turn conversations.
- Supports tool (function) calling for agents and integrations.
- Supports structured JSON output with a schema.
- Supports reasoning effort control.
- Accepts images as input (vision).
- A typical request (1,000 input / 500 output tokens) costs about $0.01.
About Meta: Muse Spark 1.2
Meta: Muse Spark 1.2 is a reasoning model from Meta, built for complex agentic tasks. It sits in the text category, and Meta positions it around workloads where the model needs to plan, reason through steps, and act rather than simply answer a single question. If you are choosing a model for an agent that has to work across several turns and tools, this is the class of model Meta intends it for.
The model accepts text, images, video, and file inputs, and it returns text. Its context window is 1,048,576 tokens, with a maximum output of 943,718 tokens. That combination matters for agentic work: a large context lets you keep long transcripts, documents, or media-derived content in view, and a large output ceiling means the model is not forced to compress a long plan or report into a short reply. Reasoning is part of the model's design, and the API exposes controls for it.
Practical use cases follow from those capabilities. Because it takes images, video, and files alongside text, you can build agents that review a document set and a screen recording, then produce a written analysis or a plan. Long context suits multi-step research, codebase or log analysis, and workflows where earlier tool results must stay available. Tool calling and structured outputs make it a reasonable fit for orchestration, where the model decides which tool to call and returns machine-readable results. The reasoning controls let you trade speed for depth depending on the task.
You call it through api14's OpenAI-compatible API using the model id "meta/muse-spark-1.2". The supported request parameters are include_reasoning, max_tokens, reasoning, reasoning_effort, repetition_penalty, response_format, structured_outputs, temperature, tool_choice, tools, top_k, and top_p. In practice, tools and tool_choice drive agentic loops, response_format and structured_outputs constrain the shape of the reply, and the reasoning parameters adjust how much internal reasoning the model does. Since the interface is OpenAI-compatible, existing clients and SDKs generally work with only the model id changed.
One limit to keep in mind is output modality: the model returns text only, so it cannot generate images or video even though it can read them. If your task is purely short-form text generation, a smaller model may be simpler and faster. For long-context, multimodal, tool-using agentic work, Muse Spark 1.2 is aimed squarely at that.
How to call the Meta: Muse Spark 1.2 API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "meta/muse-spark-1.2".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "meta/muse-spark-1.2",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
include_reasoningmax_tokensreasoningreasoning_effortrepetition_penaltyresponse_formatstructured_outputstemperaturetool_choicetoolstop_ktop_pSpecifications
- Context length
- 1,048,576
- Max output
- 943,718
- Input
- text, image, video, file
- Output
- text
Requests on api14 · last 7 days
Meta: Muse Spark 1.2: frequently asked questions
- How much does the Meta: Muse Spark 1.2 API cost?
- Meta: Muse Spark 1.2 costs Input $4.38 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of Meta: Muse Spark 1.2?
- Meta: Muse Spark 1.2 reads up to 1,048,576 tokens per request: prompt, history and documents together. It writes up to 943,718 output tokens per response.
- What can Meta: Muse Spark 1.2 do?
- Meta: Muse Spark 1.2 accepts text, image, video, file and returns text. It supports tool calling, structured JSON output, reasoning effort control.
- How do I call Meta: Muse Spark 1.2 from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "meta/muse-spark-1.2". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Meta: Muse Spark 1.2?
- Comparable Text models at a similar price: Meta: Muse Spark Open, Meta: Muse Spark 1.3, Meta: Muse Spark 1.1. Each runs through the same API key, so switching is one string.
Meta: Muse Spark 1.2 community
New topicThis community has no topics yet. Open the first one about Meta: Muse Spark 1.2.