gpt-oss-120b is 9.3× cheaper per million tokens (blended). gpt-oss-120b has the larger context window (131,072 vs 128,000 tokens). gpt-oss-120b is open-weights; the other is not.
Mercury 2 vs gpt-oss-120b
Live catalog fields. Best-in-row is highlighted.
Mercury 2
Inception · inception__mercury-2
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Identity
| Field | inception__mercury-2 | openai__gpt-oss-120b |
|---|---|---|
| Provider | Inception | OpenAI |
| Slug | inception__mercury-2 | openai__gpt-oss-120b |
| Status | live | live |
| Open weights | No | Yes |
| License | — | — |
| HuggingFace | — | openai/gpt-oss-120b |
Quality
| Field | inception__mercury-2 | openai__gpt-oss-120b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | inception__mercury-2 | openai__gpt-oss-120b |
|---|---|---|
| Input $ / 1M tokens | $0.25 | $0.02 |
| Cached input $ / 1M | $0.03 | $0.02 |
| Output $ / 1M tokens | $0.75 | $0.09 |
Context
| Field | inception__mercury-2 | openai__gpt-oss-120b |
|---|---|---|
| Max context tokens | 128,000 | 131,072 |
| Max output tokens | 50,000 | 65,536 |
Modalities
| Field | inception__mercury-2 | openai__gpt-oss-120b |
|---|---|---|
| Input | text | text |
| Output | text | text |