meta logo
meta

Meta: Muse Spark 1.3

来源介绍(英文)

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...

模型概览

模型规格

上下文
1,048,576 tokens
最大输出
943,718 tokens
架构
text+image+file+audio+video->text
分词器
Other
知识截止时间
暂未提供
内容审核
OPENROUTER

完整价格

同步自 OpenRouter。Token 价格均按每百万 Token 展示。

输入
$1.25
每百万 Token
输出
$4.25
每百万 Token
缓存读取
$0.15
每百万 Token
网页搜索
$2.5
每千次调用
API

模型配置

推理能力

是否必须推理
默认参数
medium
能力与模态
max, xhigh, high, medium, low, minimal
API

快速调用

在本地设置 OPENROUTER_API_KEY。Python 需安装 requests;JavaScript 在 Node.js 中运行。密钥应保存在服务端。

API 文档

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"meta/muse-spark-1.3","messages":[{"role":"user","content":"Hello!"}]}'
能力与模态

输入输出

输入
textimagevideofileaudio
输出
text
推理能力

· max · xhigh · high · medium · low · minimal

API

支持的 API 参数

include_reasoningmax_tokensreasoningreasoning_effortrepetition_penaltyresponse_formatstructured_outputstemperaturetool_choicetoolstop_ktop_p
可用提供方

1 提供方

核验日期: 2026年9月7日

在 OpenRouter 查看实时 Provider

Provider 可用性、延迟、吞吐量和路由会持续变化,请前往来源页面查看实时运行数据。

OpenRouter

Meta

暂未提供
上下文
1.0M
最大输出
944K
输入
$1.25
输出
$4.25
缓存读取
$0.15
缓存写入
暂未提供
meta

4 个模型

全部模型
meta logometa

Meta: Muse Spark 1.3 Contributor

Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...

上下文
1.0M
输入
text · image · video · file · audio
输出
text
输入: $0.1输出: $0.2每百万 Token
查看模型详情
meta logometa

Meta: Muse Image

Muse Image is an agentic image generation model from Meta that generates and edits images from text and reference images. Unlike single-pass image models, it reasons before it renders, breaking...

上下文
66K
输入
text · image
输出
image
图片输出: $0.01 每张图片
查看模型详情
meta logometa

Meta: Muse Spark 1.2 Contributor

Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...

上下文
1.0M
输入
text · image · video · file · audio
输出
text
输入: $0.1输出: $0.2每百万 Token
查看模型详情
meta logometa

Meta: Muse Glimmer 30B

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

上下文
131K
输入
text · image
输出
text
输入: $0.3输出: $1.1每百万 Token
查看模型详情