Muse Spark 1.2

meta/muse-spark-1.2
NewFeatured
VisionAudioToolsJSONReasoning
by Meta · 2026-08-05

Muse Spark 1.2 is Meta's reasoning model for complex agentic tasks, and the current checkpoint of the Muse Spark family. Meta describes it as an updated checkpoint over Muse Spark 1.1 with slightly higher performance, served on the same Standard tier at identical pricing — a drop-in upgrade rather than a new tier. It accepts an unusually broad input surface — text, images, video, audio, and PDF documents — and returns text, reasoning natively across modalities within a 1M-token context window. It supports configurable reasoning effort, native tool calling, and structured outputs, making it well suited for multimodal agents, deep research over mixed media, and long-context analysis. Muse Spark 1.2 targets workloads that combine documents, screenshots, recordings, and video with text — from analyzing long reports and media libraries to driving multi-step agentic pipelines that must reason over more than just text. Meta also ships muse-spark-1.2-contributor, the same checkpoint on its Contributor tier.

ctx1M tokens
Inputtext + image + video + file + audio
Outputtext
p50 TTFT1.00 s
INPUT$1.25/ 1M tokens
OUTPUT$4.25/ 1M tokens
p50 TTFT1.00 s7d
p95 TTFT2.57 s7d
TRAFFIC341tokens / 7d

Muse Spark 1.2 is a Meta-produced language model served through OrcaRouter. It accepts text, image, video, file, and audio inputs, and produces text outputs. The model has a context window of…

What is Meta Muse Spark 1.2?

Who is this model for?

What input types does it support?

How does OrcaRouter deliver this model?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="meta/muse-spark-1.2",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_tokens
  • reasoning
  • reasoning_effort
  • repetition_penalty
  • response_format
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_p

Pricing

Input / 1M tokens$1.25
Output / 1M tokens$4.25
Cache read / 1M$0.150
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $21.50 · With prompt caching $17.65

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.002150

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
1.00 s
Output speed
705 tok/s
p95 TTFT
2.57 s
Error rate
0%

Public benchmarks

Source: Design Arena

Community buzz

What developers are saying this week

Hacker News4 mentions · 7dup 4 vs the previous week

How it compares

Muse Spark 1.2Muse Spark 1.1
Input $/M$1.25$1.25
Output $/M$4.25$4.25
Context1.0M1.0M
Quality8/108/10
Compare side-by-sideCompare side-by-side

FAQ

What does Muse Spark 1.2 cost on OrcaRouter?
Input tokens are $1.25 per 1M and output tokens are $4.25 per 1M. OrcaRouter bills at the provider rate with zero markup, so these are the per-token rates you pay.
What is the context window?
The context window is 1,048,576 tokens. This is the maximum amount of input content the model can process in a single request.
What input types are supported?
Text, image, video, file, and audio. All inputs count against the same 1,048,576-token context window, and the model returns text output.
What are the main strengths?
Large context, multimodal input support, and transparent billing. It can handle long documents and mixed media in one request without using multiple specialized models.
How does it compare to smaller models?
It offers more context and more input modalities, but at a higher price per token. Use it when the task involves long or multimodal content; pick a cheaper model for short text-only work.
How does OrcaRouter handle data from requests?
The provided facts do not include data retention or privacy details. Review OrcaRouter's privacy policy and Meta's terms for the exact handling of your prompts and files.
How do I call it via an OpenAI-compatible API?
Set the base_url to https://api.orcarouter.ai/v1 and the model id to meta/muse-spark-1.2. Use standard OpenAI-compatible chat completion requests with your OrcaRouter API key.
Does Muse Spark 1.2 generate images or audio?
No. It accepts images, video, file, and audio as inputs, but its output is text. There is no indication that it generates media.
Are there benchmark scores in the provided facts?
No benchmark scores are included in the supplied metadata. You should evaluate the model on your own test set to measure quality for your specific use case.

Embed this badge

Meta: Muse Spark 1.2$1.25/M in1000ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/meta/muse-spark-1.2" target="_blank"> <img src="https://www.orcarouter.ai/embed/meta/muse-spark-1.2.svg" alt="Meta: Muse Spark 1.2 on OrcaRouter" /> </a>
Markdown [![Meta: Muse Spark 1.2](https://www.orcarouter.ai/embed/meta/muse-spark-1.2.svg)](https://www.orcarouter.ai/models/meta/muse-spark-1.2)

Model card as data

GET /api/public/models/meta/muse-spark-1.2Open
Machine-readable:/llms.txt/llms-full.txt