Muse Spark 1.3
MetaReleased Sep 2, 2026
- providers
- 1
- context
- 1.0M
- max out
- 131K
- input /M
- $1.25
- output /M
- $4.25
- cached input /M
- $0.15
- cache write /M
- $1.25
- reasoning /M
- $4.25
About
Drafted from the provider's own page.
muse-spark-1.3 is the default model in the code examples throughout these docs.
- open weights
- no
- best for
- codingextractioncompute
Capabilities
What the model accepts and returns, where a probe through our own gateway proved it.
- streaming
- tools
- json mode
- vision
- audio
Providers
What you pay through us for each provider, and its own list price where that differs.
Meta
meta/muse-spark-1.3- input /M
- $1.25
- output /M
- $4.25
- cache read /M
- $0.15
- cache write /M
- $1.25
Cache read $0.15/M · Cache write $1.25/M
cache read list price /M$0.15Not serving this model when we last asked, Oct 8, 2026.
Speed
- fastest over 24 hours
- 932.2 t/s
Fastest: Meta
- Meta11,010 ms to first token932.2 t/smedian of 24
Served
- served in the last 24 hours
- 30.00%
Across 1 provider, 12 of 40 requests
- Meta30.00% · 12 of 40
Rebuilt once a day from the requests we sent, so it is a daily figure and not a live one.
Not yet. These figures come from Artificial Analysis, which the publish pipeline reads once a day.
Integrations
What the model holds, rather than a compatibility grade: nothing here measures how well a particular tool gets on with it, so nothing here scores one.
- answers on
- chat completions
- accepts
- textimagevideopdfaudio
- returns
- text
Use this model
Not being served right now.
curl https://api.hopscotchlabs.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meta/muse-spark-1.3",
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 256
}'