Muse Spark 1.3 API in Singapore

Muse Spark is Meta’s proprietary line from Meta Superintelligence Labs — unlike Llama, its weights are not released. Version 1.3, from September 2026, is built for long agent sessions and coding across large repositories; Meta reports 75.4% on DeepSWE and 88.8% on Terminal-Bench 2.1.

Its most unusual strength is recall over long inputs: 98.1% on the MRCR test between half a million and a million tokens, so it finds what you need even at the far end of a huge document. Meta also says it is harder to trick with injected instructions, and more careful about actions that cannot be undone.

• Long coding agents across large repositories.
• Finding specific facts in very long documents.
• Multi-step agent and computer-use tasks.

• Meta’s claim of 25% fewer tokens than version 1.2 did not hold in one independent test, where cost rose 12%.
• Reportedly weaker at understanding audio than the previous version.
• Closed weights: unlike Llama, you cannot run it yourself.

Roar AI provides access to Muse Spark 1.3 through the Roar AI gateway, charged in Singapore dollars on one bill with every other model. Requests from Singapore go through our gateway in Singapore. Developers can use Muse Spark 1.3 alongside other supported models without a separate integration for every provider.

Use the OpenAI SDK you already have — point it at Roar AI and name the model. Read the docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")

reply = client.chat.completions.create(
    model="muse-spark-1.3",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

Muse Spark 1.3 is a frontier model, and requests are processed on international infrastructure, outside Singapore. The model directory says where each model is processed.

Muse Spark 1.3 vs Muse Spark 1.3 ContributorHead to head

Explore all AI models available in Singapore