meta
Meta: Muse Spark Open
meta/muse-spark-open
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
The OpenRouter catalog describes Meta's Muse Spark Open (meta/muse-spark-open) as an open-weight model tuned for agentic coding, claiming strong first-attempt accuracy, dependable tool calling, and deep codebase understanding. It accepts text, image, file, audio, and video inputs, returns text only, offers a context window of roughly one million tokens, and requires reasoning with adjustable effort. Catalog arena results look mid-pack and some evaluation fields are empty. Only OpenRouter data was supplied; an independent model card was not available in this source pack.[1]
Strengths
- Catalog-reported: an open-weight model trained for agentic coding workflows, claiming higher first-attempt accuracy, reliable tool calling, and deep codebase understanding.[1]
- Accepts text, image, file, audio, and video inputs with text output and a context window of about one million tokens.[1]
- Reasoning effort is tunable across four levels, and the endpoint advertises tool-calling and structured-output parameters.[1]
Limitations
- All evidence comes from the OpenRouter catalog; no independent model card was included in this source pack, so claimed capabilities and results should be validated on real workloads.[1]
- Reasoning is mandatory and cannot be disabled, which may matter for latency- or cost-sensitive applications.[1]
- Evaluation coverage is incomplete: the catalog lists no coding or agentic index values, and its Design Arena results appear mixed across categories.[1]
Where to use it
- Worth evaluating for agentic coding assistants that need long repository context and tool use.[1]
- A candidate for workflows that feed screenshots, files, or other multimodal inputs into a text-producing assistant.[1]
- Potentially suitable where adjustable reasoning effort and structured outputs are required; confirm fit with workload tests.[1]
Sources
- [1] OpenRouter catalog · Meta: Muse Spark OpenSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...
Specifications
- Model ID
- meta/muse-spark-open
- Canonical ID
- meta/muse-spark-open-20261015
- Creator
- meta
- Added to OpenRouter
- 15.10.2026
- Context length
- 1,048,576
- Modality
- text+image+file+audio+video->text
- Input modalities
- text, image, video, file, audio
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $1.25 / out $4.25
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | BB — next 30% of the cohort | reasoning: mandatory · default medium · efforts: xhigh, high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · default medium · efforts: xhigh, high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 24.9 | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 46.4% · rank 27 | 1,259Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 51.5% · rank 15 | 1,303Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 47.8% · rank 29 | 1,263Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 51.6% · rank 15 | 1,314Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 51.7% · rank 12 | 1,307Elo | SS — top 10% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Modal | 1,000,000 | $1.25 | $4.25 | — | — | 100% |
| Together | 1,048,576 | $1.25 | $4.25 | — | — | 100% |
| Nebiusfp4 | 1,048,576 | $1.25 | $4.25 | — | — | 100% |
| BaseTenfp4 | 1,048,576 | $1.25 | $4.25 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.