Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...
At a glance
- Context window
- 1Mtokens
- Max output
- 944Ktokens
- Knowledge to
- —
- Released
- 2026
Capabilities
Benchmarks
Design Arena
| Category | Elo | Win rate |
|---|---|---|
| models · 3d | 1,430 | 64.5 |
| models · 3d | 1,388 | 59.4 |
| models · uicomponent | 1,387 | 59.5 |
| models · uicomponent | 1,377 | 58.1 |
| models · codecategories | 1,374 | 59 |
| models · gamedev | 1,373 | 57.7 |
| models · codecategories | 1,365 | 58.2 |
| models · website | 1,365 | 59.2 |
| models · website | 1,363 | 58.5 |
| models · gamedev | 1,358 | 56.1 |
| models · dataviz | 1,330 | 55.2 |
| models · dataviz | 1,268 | 50 |
Source: Design Arena · as of Sep 16, 2026
Performance
Uptime on IranRouter
0%
Reference uptime
100%
Median latency
3,564 ms
Throughput
85.4 tok/s
IranRouter uptime comes from our own automated probes; the reference figures are daily measurements of this model's upstream routes. Each card shows a 30-day average, and a day without data stays empty.
Popularity
- Current rank
- #50
- Rank change, 7 days
- —
Daily tokens · 90 days
53.3B
Ranked by daily token volume across the global model market; the figure above the chart is the daily average.
Supported parameters
Parameters this model accepts; anything else is ignored.
Quick start
from openai import OpenAI
client = OpenAI(
api_key="ir-...",
base_url="https://iranrouter.com/v1",
)
resp = client.chat.completions.create(
model="meta/muse-spark-1.3",
messages=[{"role": "user", "content": "سلام!"}],
)
print(resp.choices[0].message.content)Only base_url and the key change; the rest of your code stays as it is.