Skip to main content
AI Choice Engine

Meta

Muse Spark 1.1

Muse Spark 1.1 is a Meta model with 1.05M context, $1.25 in / $4.25 out per million tokens, last verified October 25, 2026. Open weights: not verified. Status: Legacy; the current pick is Muse Spark 1.3. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.

The original Muse Spark API version, retained as a currently documented Standard-only endpoint with separate identity from later Spark versions.

Recorded profile verification October 25, 2026Individual provider fields may change

AI model specification details
SpecificationMuse Spark 1.1
ProviderMeta
TierBalanced
Context window1.05M
Max outputNot verifiedUnverified
Input / 1M tokens$1.25
Output / 1M tokens$4.25
WeightsNot verifiedUnverified
ParametersNot verifiedUnverified
Reasoning levelsminimal, low, medium, high, xhigh
Modalitiestext, image, video, audio, file
API model idmuse-spark-1.1
ReleasedNot verifiedUnverified

Pricing tiers: Meta Model API Standard USD/MTok input/output $1.25/$4.25, cached $0.15; no long-context premium. Search grounding adds $2.50/1,000 queries. Team limit3,000 RPM/4M TPM. Spark 1.1 has no Contributor-mode discount or Muse Code subscription access; do not copy1.2/1.3 product access.

Best for

  • Maintaining an existing1.1 integration
  • Comparing documented API versions

Watch out

Always reasons: none returns400; minimal/low/medium/high/xhigh are documented, while max is restricted to Wonder and Standard Spark 1.3. Omitted effort is model-determined. Exact output cap, parameter count and downloadable 1.1 weights/licence remain unknown. Spark Open’s weight licence, native controls and parameter count do not establish hosted1.1 identity.

Source receipts

Catalog figures for this model were checked against the following sources.

Common questions

Muse Spark 1.1

Answered from the verified figures on this page rather than general guidance.

How much does Muse Spark 1.1 cost per million tokens?
Muse Spark 1.1 lists base rates of $1.25 per million input tokens and $4.25 per million output tokens. Estimate both input and output token volume and any additional charges for your workload. Meta Model API Standard USD/MTok input/output $1.25/$4.25, cached $0.15; no long-context premium. Search grounding adds $2.50/1,000 queries. Team limit3,000 RPM/4M TPM. Spark 1.1 has no Contributor-mode discount or Muse Code subscription access; do not copy1.2/1.3 product access.
What is Muse Spark 1.1's context window?
Muse Spark 1.1 accepts about 1.05M tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.
What is Muse Spark 1.1 best for?
Muse Spark 1.1 is a balanced tier from Meta. It suits maintaining an existing1.1 integration, comparing documented api versions. Always reasons: none returns400; minimal/low/medium/high/xhigh are documented, while max is restricted to Wonder and Standard Spark 1.3. Omitted effort is model-determined. Exact output cap, parameter count and downloadable 1.1 weights/licence remain unknown. Spark Open’s weight licence, native controls and parameter count do not establish hosted1.1 identity.
Model comparison catalogBenchmark library