Head to head
GPT-3.5 Turbo vs Muse Glimmer 30B
On a blended workload of one million input tokens and three million output tokens, Muse Glimmer 30B is 1.0× cheaper than GPT-3.5 Turbo.
| GPT-3.5 Turbo | Muse Glimmer 30B | |
|---|---|---|
| Provider | OpenAI | Together AI |
| Input / MTok | $0.5 | $0.35 |
| Output / MTok | $1.5 | $1.5 |
| Cache read / MTok | — | $0.04 |
| Context window | 16,385 | 131,072 |
| Blended 1M in + 3M out | $5.00 | $4.85 |
| Status | deprecated | ga |