Today's price · per 1M tokens
Input
$0.100
per 1M tokens
Output
$0.500
per 1M tokens
Blended
$0.200
blended $/1M — 3:1 weighted input:output
Cached input
$0.004
4% of input — prompt caching
How this price is scoped: Meta Model API Standard-mode price for requests with up to 200K input tokens, per 1M tokens: input $0.10, output $0.50, cached input $0.004. Meta bills a request with more than 200K input tokens (cached tokens and a continued conversation's history count) at its long-context rates in full, not only for the tokens past 200K: input $0.30, output $1.50, cached input $0.012. Muse Ember has no discounted Contributor mode. Search grounding is billed separately at $2.50 per 1,000 queries.
Price receipt
We read Meta's own pricing page on and found muse-ember-1.0 listed with a price on the same tier — that read is where the number above comes from, recorded as a new model. We keep the page text we read; its content hash is 593dea319d.
Overview
Meta's smallest and cheapest Muse model, built to do the repeated work inside agents: sub-agent coding tasks, tool calls, routing, extraction, and batch jobs over thousands of images, files or records, while Muse Wonder or Muse Spark plans. It takes text, image, video, audio and PDF input over a 1M-token context, writes up to 524K tokens, and runs reasoning effort from "minimal" to "max". $0.10/$0.50 per 1M tokens with cached input at $0.004, which is 1/12 of Muse Spark 1.3 on input. It is API-only, with no open weights.
Capabilities
struck through = not supportedBenchmark performance
accuracy % · higher is betterWe hold no per-benchmark accuracy scores for this model yet, so it has no accuracy average. That is a gap in our coverage, not a sign the model is untested — independent evaluators often publish a composite index for a new model long before releasing its per-benchmark numbers. The percentile above is its standing across the independent composites below.
- AA Intelligence Index: 36 (max effort) (Artificial Analysis composite across reasoning, knowledge and coding evals)
- AA-Omniscience Index: 7.4 (max effort) (−100–100)
- Arena WebDev: 1608.8 ELO (Human preference on building web apps)
- Arena Agent: 0.017 (Score from real agent sessions (IPS); higher is better)
- Arena Agent cost per task: $0.02 (Median measured cost of one real Agent Arena task)
- Terminal-Bench 4.0: 40.9% (max effort)
- Cost to run the AA Intelligence Index: $0.136 per task, 3.2 min per task (max effort)
- Measured by AA: 443.5 tokens/sec output, 5.08s to first token (max effort)
- Ranks #37 of 189 comparably-measured models by percentile score, across 2 independent measurements
- Ranks #4 of 189 comparably-tested models by normalized performance per dollar top value
443.5 tokens/sec output 5.08s latency to first token (TTFT)
Throughput: Artificial Analysis, measured 2026-11-14 · Source: Artificial Analysis (artificialanalysis.ai)
Source: Artificial Analysis · updated · See full rankings →
Specifications
- Provider
- Meta
- Context window
- 1M tokens
- Modality
- text, image, video, audio
- Parameters
- Proprietary
- Open source
- No — proprietary
- Released
- Status
- Current
- Last updated
- Tags
Availability verified: — listed on Meta's own page