Skip to main content

Muse Glimmer 30B

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware.

Model card on Hugging Face
Input / output price
$0.20 / $0.80 per 1M
Context
131K tokens
Released
Aug 10, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "muse-glimmer-30b".

Read docs

Providers

4 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
EmpirioLabsempiriolabs/muse-glimmer-30b
$0.20/M$0.80/M
DeepInfradeepinfra/muse-glimmer-30b
$0.30/M$1.20/M
TogetherAItogetherai/muse-glimmer-30b
$0.35/M$1.50/M
OpenRouteropenrouter/muse-glimmer-30b
$0.35/M$1.50/M

Is a provider down? OpenRouter status

Pricing

Averaged across 4 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.30 per 1M
Average output
$1.25 per 1M
Average cache read
$0.04 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.35/MTogetherAI and OpenRouterLowest$0.20/MEmpirioLabs

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

30tokens/sacross providers

Faster than 51% of the other 599 models on the gateway

Response latency

Lower is better

1.4sacross providers

Faster than 59% of the other 780 models on the gateway

Benchmarks

The Respan Index plus 20 published scores from 2 sources, each linked to where it was published.

30.0/ 100

Respan Index#92 of 176

176 ranked models. The shaded band is this model's 95% interval, 20.2 to 53.3. GPT-5.2-Codex and Gemini 3.5 Flash-Lite fall inside it, so the gap is within the margin of error.
Muse Glimmer 30B by category: Coding 10.6, Agents 43.2, Reasoning 27.3, Knowledge & language 22.9 (estimated), Human preference 49.8
  1. 92Muse Glimmer30.0
  2. 91GPT-5.2-Codex30.1
  3. 93Gemini 3.5 Flash-Lite29.9

Published scores

BenchmarkScore
SWE-bench Verifiedhuggingface.co76%
Terminal-Bench 2.1 (Terminus-2)huggingface.co51.7%
SWE-Bench Prohuggingface.co51.2%
SciCodehuggingface.co43.6%

Compare Muse Glimmer 30B: Muse Glimmer vs Muse Wonder Full, Muse Glimmer vs Muse Wonder, Muse Glimmer vs Muse Ember, Muse Glimmer vs Muse Spark 1.3, Muse Glimmer vs Muse Spark 1.1, Muse Glimmer vs Muse Spark 1.2

Apps

Use Muse Glimmer 30B in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Muse Glimmer 30B FAQ

Short answers, built from the data on this page.

Muse Glimmer 30B is a model from Meta, released on Aug 10, 2026. Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware.

On the Respan gateway, Muse Glimmer 30B costs from $0.20 per 1M input tokens and $0.80 per 1M output tokens on EmpirioLabs, after gateway discounts. Averaged across its 4 providers, it costs $0.30 per 1M input tokens and $1.25 per 1M output tokens.

Muse Glimmer 30B is available through 4 providers: EmpirioLabs, DeepInfra, TogetherAI, and OpenRouter.

Muse Glimmer 30B accepts up to 131K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "muse-glimmer-30b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Muse Glimmer 30B scores 30.0 out of 100 on the Respan Index v1.1, ranking #92 of 176 models. By category: Coding 10.6, Agents 43.2, Reasoning 27.3, Knowledge & language 22.9 (estimated), and Human preference 49.8. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Muse Glimmer 30B has 20 published benchmark scores, including SWE-bench Verified 76%, MCP Atlas (public) 75.5%, and AIME 2026 94.7%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.