Meta: Muse Spark 1.2 pricing and limits

id meta/muse-spark-1.2 · listed 2026-08-05

Input (per 1M tokens)	$1.250
Output (per 1M tokens)	$4.250
Cached input read (per 1M)	$0.150
Context window	1,048,576 tokens
Max output	943,718 tokens
Modalities	text+image+video+file → text
Reasoning	yes

What 1,000 calls cost at 1,000 input and 300 output tokens each: $2.52.

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....

Cheaper on both input and output, with at least half the context

Model	In / 1M	Out / 1M	Context
Auto Router (Beta)	$-1000000.000	$-1000000.000	2,000,000
Pareto Code Router	$-1000000.000	$-1000000.000	2,000,000
Auto Router	$-1000000.000	$-1000000.000	2,000,000
Meta: Llama 4 Scout	$0.100	$0.300	1,310,720
OpenAI: GPT-6 Luna Pro	$0.100	$0.500	1,050,000
OpenAI: GPT-6 Luna Pro (batch)	$0.050	$0.250	1,050,000

Other meta models

Meta: Muse Spark 1.3 Contributor ($0.100 / $0.200) · Meta: Muse Spark 1.2 Contributor ($0.100 / $0.200) · Meta: Muse Glimmer 30B ($0.300 / $1.200) · Meta: Muse Spark Open ($1.250 / $4.250) · Meta: Muse Spark 1.3 ($1.250 / $4.250) · Meta: Muse Spark 1.1 ($1.250 / $4.250) · Meta: Muse Wonder ($4.000 / $20.00)

For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=meta/muse-spark-1.2 (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=meta. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Prices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with meta. Agent Exchange