Muse: Spark 1.1 API

Meta's Muse: Spark 1.1, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send muse-spark-1.1 as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: muse-spark-1.1
Maker: Meta
Context window: 1M tokens
Input price: $1.250 per million tokens
Output price: $4.250 per million tokens
Providers: 1 independent provider
Regions: global

Providers

EmpirioLabs AI: global, $1.250 input and $4.250 output per million tokens, $1.000 cache read per million tokens, 1M tokens of context

Scores

HLE: 46.2, #19 of 273
GPQA: 89.8, #46 of 250
AA-LCR: 77.7, #73 of 237
SciCode: 58.8, #12 of 123
SimpleQA Verified: 57.8, #21 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "muse-spark-1.1",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Muse: Spark 1.1?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Muse: Spark 1.1 cost?: Offers now ask $1.250 per million input tokens and $4.250 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Muse: Spark 1.1?: The largest offer takes 1,048,576 input tokens. One job can generate up to 131,072 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Muse: Spark 1.1 do?: Its providers list Audio input, Documents, Vision, Video input, Reasoning effort, JSON object, JSON schema, Frequency penalty, Presence penalty, Seed, Top-p sampling, Text, Tools.
What inputs and outputs does Muse: Spark 1.1 support?: Text · Audio · Files · Images · Video → Text.
Which providers serve Muse: Spark 1.1?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call Muse: Spark 1.1?: Send "muse-spark-1.1" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Muse: Spark 1.1 listed?: The exchange first listed it on 10/8/2026. This is not its release date.