Muse Spark 1.3 是 Meta Llama 推出的 深度推理 · 工具调用 · 结构化输出模型，上下文窗口 1,048,576 tokens，单次最大输出 131,072 tokens。
原厂描述：Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.
muse-spark-1.3数据来源：models.dev。
# Python OpenAI SDK 调用示例 import openai client = openai.OpenAI( api_key="your-api-key", base_url="https://api.eake.cn/v1" ) response = client.chat.completions.create( model="md-meta-muse-spark-1-3", messages=[ {"role": "user", "content": "你好！"} ], temperature=0.7, max_tokens=2048 ) print(response.choices[0].message.content)
https://api.eake.cn/v1
完全兼容 OpenAI API 格式，可直接使用官方 SDK 调用