Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Meta / Muse Spark

Muse Spark · original April release

First Muse release for Meta AI, preceding the public 1.1 API. Historical record of the original model and its limited API preview.

Language models (LLMs)
historicalClosed weightsGeneral purposeReasoningAgents
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
5 of 16 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedMeta AI · historical release
Output billingNot collectedNo inferred price

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
SupportedSource for Reasoning (opens in a new tab)
Tool calling
SupportedSource for Tool calling (opens in a new tab)
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2026-04-08Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Meta AI · historical release

Provider source (opens in a new tab)
API model ID
Not collected

No publicly callable selector verified for this historical/research reference.

Access
Original Meta AI app/web release with a private API preview for selected users. No current immutable public selector verified.
Regions
Historical or research deployment; no current residency commitment established

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Current Model API prices and processing policies are not applied to this historical or research-only record.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Meta AI · historical release

Not verified

No endpoint-specific discounted prompt-cache contract verified.

How it works
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Minimum reusable input
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Lifetime & refresh
Not collected

No endpoint-specific discounted prompt-cache contract verified.

How to enable it
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Usage fields
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Billing rules
Not collected

No endpoint-specific discounted prompt-cache contract verified.

Limits & data boundaries
Not collected

No endpoint-specific discounted prompt-cache contract verified.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

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.

Classification evidence (opens in a new tab)

Lifecycle dates

Provider release8 Apr 2026Source (opens in a new tab)

Sources reviewed