Muse Spark 1.1

meta/muse-spark-1.1
NewFeatured
VisionAudioToolsJSONReasoning
by Meta · 2026-07-16

Muse Spark 1.1 is Meta's multimodal reasoning model, built for agentic tasks. It accepts an unusually broad range of inputs — 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 and native tool calling, making it well suited for multimodal agents, deep research over mixed media, and long-context analysis. With efficient inference and a broad input surface, Muse Spark 1.1 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.

ctx1.05M tokens
Inputtext + image + video + file + audio
Outputtext
p50 TTFT3.00 s
INPUT$1.25/ 1M tokens
OUTPUT$4.25/ 1M tokens
p50 TTFT3.00 s7d
p95 TTFT7.24 s7d
TRAFFIC16.3Ktokens / 7d

Meta Muse Spark 1.1 is a multimodal large language model from Meta that can process text, images, video, files, and audio in a single context. Its context window is 1,048,576 tokens – roughly 1…

What is Meta Muse Spark 1.1 exactly?

Who is the target audience for this model?

How is Muse Spark 1.1 accessed through OrcaRouter?

What input modalities does the model support?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="meta/muse-spark-1.1",
    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
3.00 s
Output speed
1006 tok/s
p95 TTFT
7.24 s
Error rate
0%

Public benchmarks

71.3
AA Coding
Better than 90% of models compared
#12 of 120
50.6
AA Intelligence
Better than 84% of models compared
#20 of 122
GPQA Diamond
89.8
Humanity's Last Exam
45.1
Long-Context Recall
63.3
SciCode
58.2
tau_banking
25.2
terminalbench_v2_1
77.9
Source: artificialanalysis.ai

FAQ

What is the cost per token for Muse Spark 1.1 on OrcaRouter?
Input tokens cost $1.25 per 1 million; output tokens cost $4.25 per 1 million. There is no markup – these are the provider rates. Token count includes all modalities.
What is the context window size?
The model supports a context window of 1,048,576 tokens (approximately 1 million tokens). This includes both input and output tokens combined.
What are the main strengths of Muse Spark 1.1?
Its strengths are a very large context window and support for multiple input modalities (text, image, video, file, audio) in a single request, enabling complex multimodal reasoning without chaining models.
How does Muse Spark 1.1 compare to GPT-4 or Claude?
Direct benchmark comparisons are not publicly available. Muse Spark 1.1 offers a larger context window (1M vs typically 128K–200K) and native audio/video input, but may have different performance characteristics. Users should evaluate on their own data.
How does OrcaRouter handle my data when using this model?
OrcaRouter passes requests directly to Meta’s API. Data handling depends on Meta’s data policy; OrcaRouter does not store or process your input beyond routing. Refer to Meta’s terms for data usage details.
How do I call Muse Spark 1.1 via an OpenAI-compatible API?
Set base_url to https://api.orcarouter.ai/v1, model to "meta/muse-spark-1.1", and use standard OpenAI chat completions format with authentication via OrcaRouter API key.
Is there a minimum spend or commitment required?
No minimum spend. OrcaRouter charges only for token usage with zero markup. There is no monthly commitment.
Does the model support streaming?
No, Muse Spark 1.1 does not currently support streaming responses. All requests are synchronous.
What modalities can be included in a single request?
You can include text, images, video frames, files (e.g., PDF, Word, Excel), and audio all in one request. Each modality consumes tokens according to the model’s tokenizer.
Can I use this model for audio-to-text transcription?
Yes, the model accepts audio input and can generate text responses, but it is not a dedicated ASR model. Performance on transcription may vary; if accurate transcription is needed, consider a specialist model.

Embed this badge

Meta: Muse Spark 1.1$1.25/M in3000ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/meta/muse-spark-1.1" target="_blank"> <img src="https://www.orcarouter.ai/embed/meta/muse-spark-1.1.svg" alt="Meta: Muse Spark 1.1 on OrcaRouter" /> </a>
Markdown [![Meta: Muse Spark 1.1](https://www.orcarouter.ai/embed/meta/muse-spark-1.1.svg)](https://www.orcarouter.ai/models/meta/muse-spark-1.1)

Model card as data

GET /api/public/models/meta/muse-spark-1.1Open
Machine-readable:/llms.txt/llms-full.txt