Muse Spark 1.2

About

Muse Spark 1.2 is a closed-weight model from Meta. Meta Muse Spark 1.2. Text, multi-image, and native video. Reasoning model. It accepts text, images, and video. Context window is 1M. Released August 5, 2026.

Context window
1M
Tokens of context on a request.
License
Meta API Terms
Terms for the API.

Pricing

Token rates are US dollars per 1M tokens. Image rates are per 1K images. Audio rates are per 1M audio seconds.

Rate	Price
Input / 1M	$1.25
Cached input / 1M	$0.15
Output / 1M	$4.25

Compare

Muse Spark 1.2 is one of the catalog's detection models. The table is each model's published price, size, and context.

Model	What it does	Price	Parameters	Context
Muse Spark 1.2	Meta Muse Spark 1.2. Text, multi-image, and native video. Reasoning model.	$1.25 / 1M input	—	1M
PP-OCRv6	PaddleOCR PP-OCRv6 medium text detection and recognition; scene OCR JSONL on image chat; text returns plain text; document_url fan-out via text.	$0.02 / 1M input	20M	—
Muse Glimmer 30B	Meta Muse Glimmer 30B. Text, multi-image, and native video.	$0.35 / 1M input	30B	128K
Gemini 3.5 Flash Lite	Fastest and cheapest Gemini tier. Multimodal chat; emits no reasoning tokens.	$0.30 / 1M input	—	1M

Benchmarks

Published scores for Muse Spark 1.2, from the Gemini 3.7 Flash model card. Scores Google published for Muse Spark 1.2.

Evals

Reading	Example
Qualitative	Clear structure, grounded in the input
Quantitative	Terminal-bench 2.1: 82.9.
Cost and performance	Lower listed rate, mid-pack latency

Performance

Latency is the end-to-end round trip. Throughput is completion tokens divided by that time. It is a request rate, not decode speed.

Latency
7,296 ms
Throughput
242 tok/s
Requests
77

Methods

Methods this model serves.

Method	Returns
detection	Boxes around objects
chat	The model's reply

Estimate cost

Estimate. An hour of video is 15 frames a minute at 256 tokens a frame, plus the audio in that request, and 500 output tokens a minute.

Hours of video

$559.50

Quick start

Call this model on the OpenAI-compatible gateway. The model id is already filled in.

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

response = client.chat.completions.create(
    model="meta/muse-spark-1.2",
    messages=[{"role": "user", "content": "What is in this image?"}],
)

print(response.choices[0].message.content)