Skip to contentx402 is live on Robinhood Chain: agents can now pay for any model, per call, in USDG →
OmniRail
← All models

Meta · Language model

Muse Glimmer 30B

meta/muse-glimmer-30b
  • Language
Released Aug 9, 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. It is suited for long-horizon...

Specifications

Context window
131,072 tokens
Max output
16,384 tokens
Input
text, image
Output
text
Reasoning effort
xhigh, high, medium, low (always on)
Tokenizer
Other

Supported parameters

Accepted by the model and forwarded as-is by the gateway.

  • frequency_penalty
  • logit_bias
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • reasoning_effort
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_p

Use it

POST /api/v1/chat/completions · MCP chat · full reference

curl https://omnirail.org/api/v1/chat/completions \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"meta/muse-glimmer-30b","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'