Skip to content
Discuss your project
Model Change Index
  • OverviewNext shutdowns and latest changes
  • ShutdownsEvery date, one row per platform
  • ChangesReleases, deprecations, redirects and prices
  • LeaderboardEvery model, its scores and price
  • Check my stackYour models on one timeline
Track my stack

Muse Glimmer 30B

ActiveMetameta/muse-glimmer-30b2 platforms

What breaksAdd its dates to my calendar
Next shutdown
None setNo date on 2 platforms
List price · $ per 1M
$0.35 in $1.50 outTogether AI · cached input $0.04
Context window
131.1Ktokens

Dates on every platform

2 listings · a floor is the earliest possible date
Muse Glimmer 30B on each platform: model ID, status, dates, replacement and source
PlatformModel ID and statusDeprecatedShuts downReplacement
Together AITogether AI: Changelog (opens in a new tab) · checked Oct 14, 2026meta-models/Muse-Glimmer-30BActive–None set–
Fireworks AIFireworks AI: Muse Glimmer 30B model page (opens in a new tab) · checked Oct 14, 2026accounts/fireworks/models/muse-glimmer-30bShut downShut downNVIDIA Nemotron 3.5 Lightning 30B A3B

Removed from serverless only; dedicated deployments of this model are unaffected.

What breaks when you move off Muse Glimmer 30B

  • Availability

    Serverless requests to these model IDs stop working after the date. Dedicated deployments are unaffected.

    DeepSeek-V4-Pro, DeepSeek-V4-Flash, DeepSeek-V4-Flash-Vision-Exp, Muse Glimmer 30B, Kimi K2.6, Kimi K2.7 Code, GLM-5.2 · Fireworks AI ·

List prices

$ per 1M tokens, with each price’s source
List prices per 1M tokens, in US dollars
PlatformInputCachedOutputIn effectSource
Together AImeta-models/Muse-Glimmer-30B$0.35$0.04$1.50Aug 11, 2026CurrentTogether AI: Available models (serverless) (opens in a new tab)

Change history

ShutdownLlama 3.3 70B Instruct Turbo leaves Together serverlessTogether AI1 break

Together removes meta-llama/Llama-3.3-70B-Instruct-Turbo from serverless inference and recommends Muse Glimmer 30B.

Platform
Together AI
Replacement
Muse Glimmer 30B
  • AvailabilityRequests to the removed serverless model ID fail. The model can still run on an on-demand dedicated endpoint, billed per minute.

Source: Together AI, Deprecations (opens in a new tab)

ShutdownFireworks removes older DeepSeek, GLM, Muse and Kimi models from serverlessFireworks AI1 break

DeepSeek V4 Pro (0813), DeepSeek V4 Flash (0731), DeepSeek V4 Flash Vision Exp, Muse Glimmer 30B, Kimi K2.6, Kimi K2.7 Code and GLM 5.2 left serverless, including their Fast and US-only endpoints. Fireworks named DeepSeek V4.1 Flash, NVIDIA Nemotron 3.5 Lightning 30B A3B, GLM 5.3 and Kimi K3 as migration targets.

Platform
Fireworks AI
Announced
  • AvailabilityServerless requests to these model IDs stop working after the date. Dedicated deployments are unaffected.

Source: Fireworks AI, Changelog (opens in a new tab)

ReleaseMuse Glimmer 30B arrives on Together serverlessTogether AI

meta-models/Muse-Glimmer-30B is available on serverless with a context length of 131,072 tokens.

Platform
Together AI

Source: Together AI, Changelog (opens in a new tab); Together AI, Available models (serverless) (opens in a new tab)

ReleaseMuse Glimmer 30B launches on FireworksFireworks AI

Fireworks added Meta's Muse Glimmer 30B on serverless and on-demand deployments. It left serverless on 25 September 2026.

Platform
Fireworks AI

Source: Fireworks AI, Muse Glimmer from Meta on Fireworks: Ideal for your Always-On Agents (opens in a new tab)

Built by TeqEngine. Forward-deployed AI engineering, no model to sell. Moving an agent to a new model? Ask for a Next-Model Check.