cd /news/large-language-models/muse-spark-1-2 · home topics large-language-models article
[ARTICLE · art-88434] src=tokenstead.ai ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Muse Spark 1.2

Meta released Muse Spark 1.2, a proprietary coding model powering the Muse Code terminal agent, available only through Meta's API and routers like OpenRouter. The model features a 1M-token context window, multimodal inputs, and is priced at $1.25/M input tokens and $4.25/M output tokens on OpenRouter, with prompt caching potentially reducing effective input costs by 60-80%. Parameter count and training details remain undisclosed, and independent benchmarks are not yet available.

read1 min views1 publishedAug 9, 2026
Muse Spark 1.2
Image: Tokenstead (auto-discovered)

premierMeta’s proprietary coding model that powers the Muse Code terminal agent. Muse Spark 1.2 is not released as open weights - it is available only through Meta’s API and through API routers such as OpenRouter.

Capabilities. 1M-token context window; multimodal inputs including text, images, video, audio, and PDF documents; parallel function calling; structured output; and configurable reasoning effort. Output is text-only.

Pricing and access. On OpenRouter the model is priced at $1.25/M input tokens and $4.25/M output tokens. OpenRouter reports that prompt caching can make the effective input price 60-80% cheaper than list price. The native entry point is Meta’s Muse Code agent for macOS and Linux.

Honest framing. Parameter count, architecture, and training details have not been publicly disclosed. Independent benchmarks are not yet available, so treat vendor performance claims as preliminary.

  • 1000k
  • proprietary
  • Aug 2026

Or run it in the cloud #

Live per-provider pricing, throughput and uptime - refreshed 1 day ago via OpenRouter. Click a column to sort.

| Provider | Type | Input $/M | Output $/M | Cache $/M | Tok/s | Latency | Uptime | Value |

|---|---|---|---|---|---|---|---|---|
| API | 1.25 | 4.25 | - | - | - | - | cheapest |

Default order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are "-". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.

[Detailed API pricing page + JSON endpoint →](/models/muse-spark-1-2/pricing)

[See who runs Meta in production →](/adoption/meta)

Inference cost over time #

Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.

── more in #large-language-models 4 stories · sorted by recency
── more on @meta 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/muse-spark-1-2] indexed:0 read:1min 2026-08-09 ·