Muse: Glimmer 30B API

Meta's Muse: Glimmer 30B, 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-glimmer-30b 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-glimmer-30b
Maker: Meta
Context window: 131.1K tokens
Input price: $0.200 per million tokens
Output price: $0.800 per million tokens
Providers: 1 independent provider
Regions: global

Providers

EmpirioLabs AI: global, $0.200 input and $0.800 output per million tokens, $0.050 cache read per million tokens, 131.1K tokens of context

Scores

Intelligence: 6.3, #36 of 41
HLE: 22.0, #111 of 273
GPQA: 83.5, #87 of 250
AA-LCR: 83.3, #11 of 237
SciCode: 44.9, #80 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-glimmer-30b",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Muse: Glimmer 30B?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Muse: Glimmer 30B cost?: Offers now ask $0.200 per million input tokens and $0.800 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: Glimmer 30B?: The largest offer takes 131,072 input tokens. One job can generate up to 32,768 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Muse: Glimmer 30B do?: Its providers list Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Min-p sampling, Presence penalty, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Muse: Glimmer 30B support?: Text · Images → Text.
Which providers serve Muse: Glimmer 30B?: 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: Glimmer 30B?: Send "muse-glimmer-30b" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Muse: Glimmer 30B listed?: The exchange first listed it on 10/8/2026. This is not its release date.