Muse Spark 1.3 is a Meta model available today in Muse Code and in the Meta Model API.
Meta describes it as part of its latest rollout for coding and agentic workflows.
| Developer | Meta |
|---|---|
| Model ID | meta/muse-spark-1.3 |
| Release Date | September 2, 2026 |
| Context Window | 1,048,576 tokens (~1.0M) |
| Modalities | Image, Text → Text |
| Capabilities | file input, parallel tool calls, reasoning, streaming, structured (JSON schema) output, tool/function calling, vision, web search |
Availability
Muse Spark 1.3 is rolling out in Muse Code and the Meta Model API.
Launch timing
Meta’s announcement for Muse Spark 1.3 was published on September 2, 2026.
Product positioning
The model is presented as Meta’s newest update in its Muse Spark line.
Reported focus
Coverage around the release says the update improves coding and agentic work performance.
Coding workflows
Muse Spark 1.3 is available in Muse Code, indicating use in coding-focused workflows.
API-based integration
The model is also available through the Meta Model API for developer integration.
Sources: https://research.meta.ai/blog/introducing-muse-spark-1-3 · https://www.datacamp.com/blog/muse-spark-1-3 · https://codersera.com/blog/muse-spark-complete-guide-2026/
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Muse Spark 1.3 is documented as suited for agentic workflows, including multi-step tool use, browser-based tasks, and long-horizon work in a single thread. It is also positioned for software engineering and coding assistance, with improved coding performance and long-running coding tasks across repositories.
It is documented for use with chat completion, image understanding, video and audio understanding, tool calling, structured output, and search grounding. It is also described as useful for web research and automation, professional and computer-use agents, and long-context retrieval.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "meta/muse-spark-1.3", "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-1.3", "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-1.3","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
The documented pricing caveat is that Muse Spark 1.3 has a separate contributor tier that is cheaper but allows Meta to use your prompts and completions to improve its products, while the standard tier keeps data private and costs more.
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 48.2 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Coding | 75.8 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| OSWorld | 66.9 | Computer-use across real desktop applications | Source | September 21, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Muse Spark 1.3 This page | Agentic workflows and structured output | |||
| Long-context multimodal reasoning and tool use | ||||
| Agentic tasks, computer use & coding | ||||
| Multimodal reasoning and tool use |
Muse Spark 1.3 has a 1,048,576 tokens context window.
Muse Spark 1.3 takes image, text as input and returns text.
Use meta/muse-spark-1.3 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Muse Spark 1.3 became available on September 2, 2026.
Muse Spark 1.3 is priced at input $1.71925 / 1M tokens, output $5.84545 / 1M tokens, cached input $0.20631 / 1M tokens.
Yes, Muse Spark 1.3 can stream responses as they are generated.
Yes, Muse Spark 1.3 accepts image input alongside text.
Muse Spark 1.3 was built by Meta.
Yes, it supports function calling along with parallel tool calls and structured outputs.
