Muse Spark 1.2 is a multimodal chat model from Meta, accepting text and image input and returning text output. It supports a 1,048,576-token context window, suitable for long documents, codebases and multi-turn conversations that need to retain a large amount of context.
The model supports reasoning, streaming responses, structured outputs, function/tool calling, vision (image understanding), file input and web search, making it suitable for agentic and research-oriented applications.
Released August 5, 2026.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Muse Spark 1.2 is documented as suited for real coding workflows, including code generation, complex debugging, codebase understanding, and end-to-end developer workflows.
It is also documented as suited for long-running tasks that can run start to finish in one session.
The model is documented for multimodal tasks, including turning visuals into working code and translating perception into physical action.
It is also documented for robust audio-visual understanding, including video-heavy workflows common in real-world enterprise use.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "meta/muse-spark-1.2", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "meta/muse-spark-1.2", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"meta/muse-spark-1.2","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 39.8 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Coding | 72.2 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Muse Spark 1.2 This page | Long-context multimodal reasoning and tool use | |||
| Frontier reasoning + agents | ||||
| Reasoning + agents | ||||
| Complex agentic coding and enterprise workflows | ||||
| Long-context, multimodal & agentic workflows |
Muse Spark 1.2 has a 1,048,576 tokens context window.
Muse Spark 1.2 takes image, text as input and returns text.
Use meta/muse-spark-1.2 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Muse Spark 1.2 became available on August 5, 2026.
Muse Spark 1.2 is priced at input $1.71925 / 1M tokens, output $5.84545 / 1M tokens, cached input $0.20631 / 1M tokens.
Yes, Muse Spark 1.2 can stream responses as they are generated.
Yes, Muse Spark 1.2 accepts image input alongside text.
Muse Spark 1.2 was built by Meta.
Yes, it supports tool calling, including parallel tool calls and function calling.
Yes, web search is listed among its supported features and capabilities.
