LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Muse Spark 1.1

meta·meta/muse-spark-1.1·GA·Closed·muse series·NEW
Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.

Muse Spark 1.1 by meta is offered by 12 providers on this page. Its official list price is $1.25 per 1M input tokens and $4.25 per 1M output tokens.

Artificial Analysis rates it 53.2 on the Intelligence Index, with 71.3 for coding and 39.7 for agentic tasks. Against its lowest blended price of $2.00 per 1M, that is roughly 27 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 199 tokens per second, with 1.41s to the first token. Running one task of the Artificial Analysis suite costs about $0.2923, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, PDF, Video, and Audio. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.

Specs & pricing

Input / output per 1M tokens
Official price·Meta
$1.25 / $4.25
Blended $2.00 · Cache read $0.15
Lowest paid·NanoGPTGateway
$1.25 / $4.25
Blended $2.00 · 1× spread
Context
1,048,576
Output limit
131,072
Knowledge cutoff
—
Released / updated
2026-04-08 / 2026-07-09
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDFVideoAudio

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier xhigh

Intelligence53.2
Value27
Coding71.3
Agentic39.7
Output speed199 tok/s
TTFT1.41 s
Cost per task$0.2923
Value formulaIQ 53.2 ÷ min blended $2.000 = 27

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

Available at 12 providers12 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPTGateway$1.25$4.25$0.15—1,000,000 ⚠65,536
OrcaRouterGateway$1.25$4.25$0.15—1,048,576131,072
PioneerGateway$1.25$4.25$0.15$1.251,048,576131,072
Vercel AI GatewayCloud$1.25$4.25$0.15—1,048,5761,048,576
MetaOfficialFirst-party$1.25$4.25$0.15—1,048,576131,072
DevPass (LLM Gateway)Gateway$1.25$4.25$0.15—1,048,576131,072
EmpirioLabs AI
muse-spark-1-1
Gateway$1.25$4.25$1.00—1,048,576131,072
Kilo GatewayGateway$1.25$4.25$0.15—1,048,576943,718
Merge GatewayGateway$1.25$4.25$0.15—1,048,576262,144
AbacusGateway$1.25$4.25$0.15—1,000,000 ⚠32,000
OpenRouterGateway$1.25$4.25$0.15—1,048,576943,718
LLM GatewayGateway$1.25$4.25$0.15—1,048,576131,072

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.

Your usage cost

1NanoGPT$330.50
2OrcaRouter$330.50
3Pioneer$330.50
4Vercel AI Gateway$330.50
5Meta · Official$330.50
6DevPass (LLM Gateway)$330.50
Switch to NanoGPT to save $0.00/mo (0%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark11 items

NameConditionsScoreMetricSource
SWE-Bench Pro—61.5resolve rateSource ↗
Terminal-Benchv2.180success rateSource ↗
DeepSWEv1.153.3resolve rateSource ↗
MCP Atlas—88.1success rateSource ↗
JobBench—54.7success rateSource ↗
Toolathlon-Verified—75.6success rateSource ↗
Humanity's Last Examvariant: with tools62.1accuracySource ↗
OSWorld-Verified—80.8success rateSource ↗
Finance Agentvv257.2accuracySource ↗
CharXiv Reasoning—88.4accuracySource ↗
BabyVision—76.3accuracySource ↗

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

Reasoning control

effort = minimaleffort = loweffort = mediumeffort = higheffort = xhigh

2 / 12 providers expose no reasoning control (reasoning_options: []).

Related models

Muse Spark 1.3same series$1.25 / $4.25Muse Spark 1.3 Contributorsame series$0.10 / $0.20Muse Image 1.0same series—DeepSeek V4 Flashcheaper alternative$0.14 / $0.28DeepSeek V4 Procheaper alternative$0.435 / $0.87GLM-5.3-Flashcheaper alternative$0.075 / $0.25DeepSeek V4 Flash 0731cheaper alternative$0.445 / $1.34

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$4.25$02026-08-052026-08-132026-08-05 · Input list $1.252026-08-06 · Input list $1.252026-08-07 · Input list $1.252026-08-08 · Input list $1.252026-08-09 · Input list $1.252026-08-10 · Input list $1.252026-08-11 · Input list $1.252026-08-12 · Input list $1.252026-08-13 · Input list $1.252026-08-05 · Output list $4.252026-08-06 · Output list $4.252026-08-07 · Output list $4.252026-08-08 · Output list $4.252026-08-09 · Output list $4.252026-08-10 · Output list $4.252026-08-11 · Output list $4.252026-08-12 · Output list $4.252026-08-13 · Output list $4.252026-08-05 · Min blended $2.002026-08-06 · Min blended $2.002026-08-07 · Min blended $2.002026-08-08 · Min blended $2.002026-08-09 · Min blended $2.002026-08-10 · Min blended $2.002026-08-11 · Min blended $2.002026-08-12 · Min blended $2.002026-08-13 · Min blended $2.00
Data partly from models.dev (MIT) · Meta official docs ↗