Meta's Muse Spark Open, 816B params with 1M context, goes live on ai& inference
DavidBennett__ · x · 2026-11-11
Japanese inference provider ai& says it is the first to serve Meta's first open-weight large model, Muse Spark Open, externally.
Key specs from the listing: 816B parameters, a 1M-token context window, priced at $1.25/M input tokens, $0.15/M cached input, and $4.25/M output, with zero data retention on their infrastructure. Note: the model name and specs come from a third-party post, not yet confirmed by Meta officially.
More from Infra
- HF tokenizers v1.0.0-rc.4 restores Python APIs and encodes up to 17x faster — art_zucker · 2026-11-11
- MacPaw's Elix claims fastest LLM inference on Apple silicon, winning all 33 benchmarks — JosephJacks_ · 2026-11-11
- Which tasks have you fully moved from cloud models to local ones? — FulcraDynamics · 2026-11-11
- X's recommender is multimodal: CLIP and MultimodalPostEmbedderV5 embeddings feed Phoenix retrieval — cocktailpeanut · 2026-11-11
- NEAR AI discloses breach: SGLang RCE flaw let attacker reach infra, ~100 users' data exposed — bingxu_ · 2026-11-11
- Bittensor launches Gamma Tokens for native agent payments across subnets — markjeffrey · 2026-11-11