gpt-oss-120b is 12.0× cheaper per million tokens (blended). gpt-oss-120b has the larger context window (131,072 vs 8,192 tokens, 16.0×).
Gemma 2 27B vs gpt-oss-120b
Live catalog fields. Best-in-row is highlighted.
Gemma 2 27Bopen
Google · google__gemma-2-27b-it
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Identity
| Field | google__gemma-2-27b-it | openai__gpt-oss-120b |
|---|---|---|
| Provider | OpenAI | |
| Slug | google__gemma-2-27b-it | openai__gpt-oss-120b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | google/gemma-2-27b-it | openai/gpt-oss-120b |
Quality
| Field | google__gemma-2-27b-it | openai__gpt-oss-120b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | google__gemma-2-27b-it | openai__gpt-oss-120b |
|---|---|---|
| Input $ / 1M tokens | $0.65 | $0.02 |
| Cached input $ / 1M | — | $0.02 |
| Output $ / 1M tokens | $0.65 | $0.09 |
Context
| Field | google__gemma-2-27b-it | openai__gpt-oss-120b |
|---|---|---|
| Max context tokens | 8,192 | 131,072 |
| Max output tokens | 2,048 | 65,536 |
Modalities
| Field | google__gemma-2-27b-it | openai__gpt-oss-120b |
|---|---|---|
| Input | text | text |
| Output | text | text |