Skip to main content
MetaOct 15, 2026

Muse Spark Open

muse-spark-openPrivateOpen weights

Muse Spark Open is an open-weight reasoning model from Meta for coding and agentic workflows. It supports tool calling and native image understanding in a single checkpoint, using a sparse Mixture-of-Experts architecture with 816B total / 42B active parameters and a 1M-token context window.

$1.56/$5.31
per 1M in / out
1M
context window
128K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 24%71.7%
Blended pricecheaper than 40%$2.50
Context windowlarger than 88%1M
Max outputlarger than 78%128K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InTextImage
OutText

Not supportedvideo input, audio input, X search and log probabilities

Benchmarks

GPQA Diamond
71.7%106th of 139 · 56 score higher for less, including Gemini 3.8 Flash, Gemini 3.7 Flash and Pareto

Specs

Model ID
muse-spark-open
Endpoint
POST /api/v1/chat/completions
Context window
1,048,576 tokens
Max output
131,072 tokens
Reasoning
low · medium · high · xhigh · default xhigh
Precision
Not disclosed
Privacy
Private
Added
Oct 15, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
Muse Spark Open$1.56$5.3171.7%1M128K——
DeepSeek V4.1 Flash 1017 Ultrafast$1.50$6.0088.9%1M128K——
DeepSeek V4 Pro 0813$1.65$4.9582.3%1M256K——
GLM 5.3 E2EE$1.75$5.5075.3%1M32K——
Qwen 4 Max$1.50$4.5094.4%1M384K——

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$1.56per 1M tokens
Cached input$0.187588% off input
Output$5.31per 1M tokens

Estimate a workload

$0.0058per request
$57.81for 10,000 requests

Blended price against similar models

Muse Spark Open$2.50

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "muse-spark-open",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "xhigh"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelmuse-spark-openRequired
messagestext · image_urlContent parts the model reads
max_completion_tokensUp to 131,072Counts reasoning tokens
reasoning_effortlow | medium | high | xhighDefault xhigh
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations