Muse Glimmer 30B
requesty/muse-glimmer-30b · family muse · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
—
Cache read $/1M
#428 of 7,908
Cheapest rank
- Provider
- Requesty (
requesty) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 20,480 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Muse Glimmer 30B” is offered by 9 providers — cheapest-effective first. This one (Requesty) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Requesty (this) | free | free | $0.00 | 131k |
| Nvidia | free | free | $0.00 | 131k |
| EmpirioLabs AI | $0.2 | $0.8 | $0.35 | 131k |
| Vultr | $0.25 | $1 | $0.44 | 131k |
| Kilo Gateway | $0.3 | $1.1 | $0.50 | 131k |
| DevPass (LLM Gateway) | $0.3 | $1.2 | $0.52 | 131k |
| NanoGPT | $0.35 | $1.5 | $0.64 | 131k |
| OpenRouter | $0.35 | $1.5 | $0.64 | 131k |
| Vercel AI Gateway | $0.35 | $1.5 | $0.64 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Requesty 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):