Docs constrain generated reasoning plus visible output by a model-specific maximum and shared context budget, but do not publish a numeric model maximum.
Standard request content is not used to train Meta models.
INPUT / 1M TOKENS$1.25
OUTPUT / 1M TOKENS$4.25
Standard mode. No long-context premium. Reasoning tokens are billed as output; web search is additional. Cached input price: $0.15 / 1M tokens (base tier).
Standard requests are not used to train Meta models. Terms allow retention for service operation, safety/security, legal and policy purposes without a fixed general duration. Standard mode is not itself a zero-retention guarantee.
Not guaranteed: entries may be evicted early. The guide gives no fixed inactivity TTL.
How to enable it
No flags required. Optional prompt_cache_key on Responses and Chat Completions groups related requests; prompt_cache_retention is Responses-only.Source for How to enable it (opens in a new tab)
Standard mode. No long-context premium. Reasoning tokens are billed as output; web search is additional.
Observed 13 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.
Caching reviewed 13 Oct 2026
What the measurements say
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Meta identifies this native Muse model in its research or hosted-model catalog. The reviewed release is available through provider-controlled service, subscription or research preview, without a released weight artifact in the reviewed inventory. The September Spark roadmap still describes its weight release as forthcoming. Open-weight Glimmer, SAM and Llama are excluded separately; hosted access alone does not turn those models into closed models.