DeepInfra

Muse Glimmer 30B

meta-models
Chat

Muse Glimmer is a 30B multimodal agentic model distilled from Muse Spark — reasoning, tool use, and failure recovery in a single model that runs locally on consumer hardware.

Modalities

In / out price

$0.30 / $1.10

per 1M

Cached price

$0.04

per 1M

Context

131K

Max output

131K

Released

Providers

2 routes

The same model can have different pricing and privacy guarantees depending on who serves it. The model's headline privacy uses the strongest available route below. Discovered routes awaiting approval remain listed as not live.

ProviderPrivacyInput / 1MOutput / 1MCache read / 1MContextMax outputUptimeLatencyThroughput
DeepInfraDeepInfraNot live
Private$0.30$1.20$0.04131K16K
Phala AINot live
Private$0.30$1.10$0.04131K131K

Privacy

2 / 4

Private routing

Private tier

  1. Anonymous
  2. Private
  3. TEE
  4. E2EE

Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more

Features

5
Streaming
Tool calling
Vision
Reasoning
Prompt caching

Uptime

Muse Glimmer 30B — AnonRouter Models