tokenstat
tokenstat

Meta: Muse Spark Open

meta/muse-spark-open · rates as of · How this catalog is built · Benchmarks

Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.

Cheapest input
$1.25
$/MTok · models.dev
Cheapest output
$4.25
$/MTok
Context
1.0M
tokens
Sources
3
21 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestmeta/muse-spark-openAi&$1.25$4.25$0.151.0M
models.devmeta/muse-spark-openCloudflare$1.25$4.25$0.151.0M
models.devmeta/muse-spark-openKilo Gateway$1.25$4.25$0.151.0M
models.devmeta/muse-spark-openMerge Gateway$1.25$4.25$0.151.0M
models.devmeta/muse-spark-openNanoGPT$1.25$4.25$0.151.0M
OpenRoutermeta/muse-spark-openOpenRouter$1.25$4.25$0.151.0M
models.devmeta/muse-spark-openPrime Inference$1.25$4.25$01.0M
models.devmeta/muse-spark-openVercel AI Gateway$1.25$4.25$0.151.0M
models.devfireworks_ai/accounts/fireworks/models/muse-spark-openEden AI$1.25$4.25$0.151.0M
models.devaccounts/fireworks/models/muse-spark-openFireworks AI$1.25$4.25$0.151.0M
models.devmeta-models/muse-spark-openNebius$1.25$4.25$0.151.0M
models.devmuse-spark-openOllama Cloud$1.25$4.25$0.151.0M
models.devmuse-spark-openRequesty$1.25$4.25$0.151.0M
LiteLLMmeta/muse-spark-openN/A$1.25$4.25$0.15N/A
LiteLLMaccounts/fireworks/models/muse-spark-openN/A$1.25$4.25$0.15N/A
LiteLLMmeta-models/muse-spark-openN/A$1.25$4.25$0.15N/A
LiteLLMmuse-spark-openN/A$1.25$4.25$0.15N/A
LiteLLMbaseten/meta-models/muse-spark-openN/A$1.25$4.25$0.15N/A
models.devmuse-spark-openCharm Hyper$1.40$4.65$0.171.0M
models.devmuse-spark-openVenice AI$1.56$5.31$0.18751.0M
LiteLLMkyma/muse-spark-openN/A$1.69$5.74$0.1688N/A

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • In: video
  • In: audio
  • In: pdf
  • In: file
  • Out: text
Knowledge cutoff: 2026-01-04Released: 2026-10-15Output limit: 944K tokensFamily: muse

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.