gpt-oss-120b is 13.9× cheaper per million tokens (blended).
Muse Glimmer 30B vs gpt-oss-120b
Live catalog fields. Best-in-row is highlighted.
Muse Glimmer 30Bopen
Meta · meta__muse-glimmer-30b
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Identity
| Field | meta__muse-glimmer-30b | openai__gpt-oss-120b |
|---|---|---|
| Provider | Meta | OpenAI |
| Slug | meta__muse-glimmer-30b | openai__gpt-oss-120b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | meta-models/Muse-Glimmer-30B | openai/gpt-oss-120b |
Quality
| Field | meta__muse-glimmer-30b | openai__gpt-oss-120b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | meta__muse-glimmer-30b | openai__gpt-oss-120b |
|---|---|---|
| Input $ / 1M tokens | $0.30 | $0.02 |
| Cached input $ / 1M | $0.04 | $0.02 |
| Output $ / 1M tokens | $1.20 | $0.09 |
Context
| Field | meta__muse-glimmer-30b | openai__gpt-oss-120b |
|---|---|---|
| Max context tokens | 131,072 | 131,072 |
| Max output tokens | 16,384 | 65,536 |
Modalities
| Field | meta__muse-glimmer-30b | openai__gpt-oss-120b |
|---|---|---|
| Input | text, image | text |
| Output | text | text |