jishie

Muse Glimmer 30B

vultr/muse-glimmer-30b · family muse · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.

$0.44
Blended $/1M (3:1)
$0.25
Input $/1M
$1
Output $/1M
$1.25
1M in + 1M out
—
Cache read $/1M
#3057 of 9,440
Cheapest rank
Provider
Vultr (vultr)
Kind
text (outputs text)
Context
131,072 tokens
Max output
131,072 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Muse Glimmer 30B” is offered by 12 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Kenarifreefree$0.00131k
Nvidiafreefree$0.00131k
Requestyfreefree$0.00131k
Doubleword$0.11$0.32$0.16131k
EmpirioLabs AI$0.2$0.8$0.35131k
Vultr (this)$0.25$1$0.44131k
Kilo Gateway$0.3$1.2$0.52131k
DevPass (LLM Gateway)$0.3$1.2$0.52131k
NanoGPT$0.35$1.5$0.64131k
Vercel AI Gateway$0.35$1.5$0.64131k
OpenRouter$0.35$1.5$0.64131k
AI/ML API$0.3703$1.59$0.67131k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Vultr and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"muse-glimmer-30b","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Vultr models · model index · JSON