Muse Spark 1.1
meta/muse-spark-1.1- Meta
- Family · Muse Spark 1
- Released 9 Jul 2026
- Text · Image · Video · File → Text
- Reasoning · adjustable
- Tools · JSON · Vision
Not on OSMEXO yet
Spec & list price
Context1M
Max output944K
Input / 1M$1.25
Output / 1M$4.253.4× input
Scores · standing
Intelligence33.7#54/490
Coding71.3#24/196
Usage
Tokens / day497.6M▲ 120% 7d
Usage rank#234
Requests / day10.4K
Tool calls / req0.37
Per request · 30 days
Avg input18.7K1.3× median
Avg output1.1K1.6× median
Cache hit65%about median
Reasoning share63%1.1× median
Tool-call failures0.5%0.3× median
Consumption
Peak 1.5B 4 OctLow 33.0M 24 OctRank today #234
News & trends
12 mentions this week ▲ 300%Muse Spark 1 family · videos, posts, articles · 30 days
Trending · 14 days · Muse Spark 1 family
- Cliffside Library: DeepSeek V4.1 Flash vs Muse Spark 1.3 | Voxel Battle 02111 views
- Obsidian Forge: Muse Spark 1.3 vs Gemini 3.1 Pro | Shader Battle 11188 views
News · latest from Meta
- Meta Networking at the 2026 OCP Global Summit: Open Innovation for Scale-Up, Scale-Out, and Scale-Across AI NetworksMeta Engineering · 26 Oct
- Scale Agentic Coding Workflows with Meta’s Muse Spark Open on NVIDIA GB300 NVL72NVIDIA · 15 Oct
- Meta Muse Spark Open is live on Together AITogether AI · 15 Oct
- Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta15 Oct
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across providers, latest day
Output speed#14/331208 tok/s3.3× faster than median
First token#2411.91 s1.8× longer than median
#5 cheapest of 9 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Family progress
Intelligence Index
- Family releases48.1
Technical details
- Reasoning
- on · medium
- Tokenizer
- Other
- Moderation
- moderated
Reasoning effort
- xhigh
- high
- medium · default
- low
- minimal
Request parameters 12
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- reasoning_effort
- include_reasoning
- temperature
- top_p
- top_k
+2 more
- max_tokens
- repetition_penalty
Interesting facts
- 7.4× the output room of similar models (943.7K against a 128.0K median).
- Weekdays average 214.9M tokens a day against 268.7M on weekends.
When to use
Best for
- Coding agents that edit large codebases
- Hard science and reasoning questions
- Analysis of very long documents
- Image and video understanding
- Agents with tool calling and structured output
Think twice for
- Low-cost bulk classification
- Self-hosting (closed weights)
- Image generation
Research papers
Same family
Muse Spark 1- 48.1
- 39.6
Alternatives
other vendors · similar capability- 36.0
- 38.2
- 30.1
- 29.7
Want Muse Spark 1.1 on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.