LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Muse Ember

meta·meta/muse-ember-1.0·GA·Closed·muse series·NEW
Muse Ember is Meta's smallest and most efficient reasoning model, built for the work agents repeat all day: tool calls, coding subtasks, routing, extraction, and long-document parsing. It pairs with Muse Wonder or Muse Spark, which plan while Muse Ember handles the volume.

Specs & pricing

Input / output per 1M tokens
Official price·Meta
$0.10 / $0.50
Blended $0.20 · Cache read $0.004
Lowest paid·MetaFirst-party
$0.10 / $0.50
Blended $0.20 · 1.7× spread
Context
1,048,576
Output limit
524,288
Knowledge cutoff
—
Released / updated
2026-11-09 / 2026-11-09
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImageVideoPDFAudio
References
Announcement

Muse Ember by meta is offered by 10 providers on this page. Its official list price is $0.10 per 1M input tokens and $0.50 per 1M output tokens. No paid channel is priced below the official list price. Prices vary about 1.7× across the providers that host it.

Artificial Analysis rates it 36 on the Intelligence Index, with 48.7 for Strategy & Ops, its strongest domain. Against its lowest blended price of $0.20 per 1M, that is roughly 180 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 604 tokens per second, with 8.63s to the first token. Running one task of the Artificial Analysis suite costs about $0.1359, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 1,048,576 tokens, with an output limit of 524,288 tokens. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Video, PDF, and Audio.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Max

Intelligence36
Value180
Engineering41.8
Finance & Accounting44.6
Legal38.5
Healthcare & Medical41.3
Strategy & Ops48.7
Economics41
Output speed604 tok/s
TTFT8.63 s
Cost per task$0.14
Value formulaIQ 36 ÷ min blended $0.200 = 180
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
XhighIQ 34.1 · 561 tok/s
MaxIQ 36 · 604 tok/s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 10 providers10 with public prices

  • ProviderInput / Output
  • MetaOfficialFirst-party
    $0.10 / $0.50
    tiered >200K: $0.30
    Cache read $0.004Context 1,048,576Output limit 524,288
  • DevPass (LLM Gateway)Gateway
    $0.10 / $0.50
    Cache read $0.004Context 1,048,576Output limit 524,288
  • LLM GatewayGateway
    $0.10 / $0.50
    Cache read $0.004Context 1,048,576Output limit 524,288
  • OpenCodeGateway
    $0.10 / $0.50
    tiered >200K: $0.30
    Cache read $0.004Context 1,048,576Output limit 270,000
  • Cloudflare AI GatewayCloud
    $0.10 / $0.50
    Cache read $0.004Context 1,048,576Output limit 524,288
  • OpenRouterGateway
    meta/muse-ember
    $0.10 / $0.50
    Cache read $0.004Context 1,048,576Output limit 943,718
  • Vercel AI GatewayCloud
    meta/muse-ember
    $0.10 / $0.50
    Cache read $0.004Context 1,048,576Output limit 1,048,576
  • NanoGPTGateway
    meta/muse-ember
    $0.10 / $0.50
    Cache read $0.004Context 1,048,576Output limit 1,048,576
  • Kilo GatewayGateway
    meta/muse-ember
    $0.10 / $0.50
    Cache read $0.004Context 1,048,576Output limit 943,718
  • KenariGateway
    muse-ember-1-0
    $0.17 / $0.86
    Cache read $0.0086Context 1,048,576Output limit 524,288
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
MetaOfficialFirst-party$0.10
tiered >200K: $0.30
$0.50$0.004—1,048,576524,288
DevPass (LLM Gateway)Gateway$0.10$0.50$0.004—1,048,576524,288
LLM GatewayGateway$0.10$0.50$0.004—1,048,576524,288
OpenCodeGateway$0.10
tiered >200K: $0.30
$0.50$0.004$01,048,576270,000
Cloudflare AI GatewayCloud$0.10$0.50$0.004—1,048,576524,288
OpenRouter
meta/muse-ember
Gateway$0.10$0.50$0.004$0.131,048,576943,718
Vercel AI Gateway
meta/muse-ember
Cloud$0.10$0.50$0.004—1,048,5761,048,576
NanoGPT
meta/muse-ember
Gateway$0.10$0.50$0.004—1,048,5761,048,576
Kilo Gateway
meta/muse-ember
Gateway$0.10$0.50$0.004—1,048,576943,718
Kenari
muse-ember-1-0
Gateway$0.17$0.86$0.0086—1,048,576524,288

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = minimaleffort = loweffort = mediumeffort = higheffort = xhigheffort = maxeffort = none

Your usage cost

Common scenarios
1Meta · Official$33.48
2DevPass (LLM Gateway)$33.48
3LLM Gateway$33.48
4OpenCode$33.48
5Cloudflare AI Gateway$33.48
6OpenRouter$33.48
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input list $0.10Output list $0.50Min blended $0.20

Price history accumulates from each data sync; currently only 1 sample(s) (2026-11-10). Each future sync adds a point, and once accumulated a line is drawn here.

Benchmark9 items

NameConditionsScoreMetricSource
AutomationBenchvariant: max effort; Artificial Analysis AutomationBench-AA37.8strict pass@1Source ↗
Agents' Last Examharness: Meta internal evaluation framework · variant: max effort · dataset: Linux subset61.6scoreSource ↗
Terminal-Benchharness: mini-swe-agent · variant: max effort · v4.040.9accuracySource ↗
FrontierCodevariant: max effort; Artificial Analysis FrontierCode-AA · v2.027.2scoreSource ↗
GDP.pdfvariant: max effort; Artificial Analysis GDP.pdf-AA22.8scoreSource ↗
OSWorldvariant: max effort · v2.169.5mean partial scoreSource ↗
OSWorldvariant: max effort · v2.133.8binary completion rateSource ↗
PerceptionBenchharness: Meta internal evaluation framework · variant: max effort; with tools80.6scoreSource ↗
Artificial Analysis Intelligence Indexvariant: max effort · v536index scoreSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Artificial Analysis evaluations12 items

HLE-Diamond25.1%
CritPt v2 Hard39.0%
FrontierCode 2.027.2%
Terminal-Bench 4.040.9%
Terminal-Bench-Science20.0%
AutomationBench-AA68.1%
AA-Briefcase1521
GDP.pdf22.8%
MLCR-AA18.3%
AA-Omniscience Index7.4
AA-Omniscience Accuracy21.1%
AA-Omniscience Non-Hallucination82.6%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Muse Spark Opensame series—Muse Wondersame series$4.00 / $20.00Muse Wonder Fullsame series—Nemotron 3 Ultra 550B A55Bcheaper alternative$0 / $0Nemotron 3.5 Super VL 120B A12Bcheaper alternative$0 / $0reBeam 1.0 501B A23Bcheaper alternative$0 / $0Qwen3.7 Flashcheaper alternative$0.03 / $0.13Llama Prompt Guard 2 86Msame lab—Muse Glimmer 30Bsame lab—
Data partly from models.dev (MIT) · Meta official docs ↗