All models

Muse Glimmer 30B

Stable

Meta · Released 2026-08 · meta/muse-glimmer-30b

Overview

Open-weight model from Meta's Muse family — the successor to Llama — built for self-hosting, fine-tuning and high-throughput production workloads. Muse Glimmer 30B supports up to 131K tokens of context, native vision input. Served through the FirmLink unified API with OpenAI-compatible endpoints.

Function CallingJSON ModeStreamingTextVision

API example

Fully OpenAI-compatible — just change the model field.

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

Pricing

Input$0.35 /1M
Output$1.50 /1M
Context window131K
Max output8K
Muse Glimmer 30B is provided by Meta and served through the FirmLink gateway. Availability and limits follow the provider's terms.