gpt-oss-120b is 32.4× cheaper per million tokens (blended). gpt-oss-120b has the larger context window (131,072 vs 65,536 tokens, 2.0×). gpt-oss-120b is open-weights; the other is not.
Nano Banana 2 (Gemini 3.1 Flash Image Preview) vs gpt-oss-120b
Live catalog fields. Best-in-row is highlighted.
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
Google · google__gemini-3.1-flash-image-preview
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Identity
| Field | google__gemini-3.1-flash-image-preview | openai__gpt-oss-120b |
|---|---|---|
| Provider | OpenAI | |
| Slug | google__gemini-3.1-flash-image-preview | openai__gpt-oss-120b |
| Status | live | live |
| Open weights | No | Yes |
| License | — | — |
| HuggingFace | — | openai/gpt-oss-120b |
Quality
| Field | google__gemini-3.1-flash-image-preview | openai__gpt-oss-120b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | google__gemini-3.1-flash-image-preview | openai__gpt-oss-120b |
|---|---|---|
| Input $ / 1M tokens | $0.50 | $0.02 |
| Cached input $ / 1M | — | $0.02 |
| Output $ / 1M tokens | $3.00 | $0.09 |
Context
| Field | google__gemini-3.1-flash-image-preview | openai__gpt-oss-120b |
|---|---|---|
| Max context tokens | 65,536 | 131,072 |
| Max output tokens | 58,982 | 65,536 |
Modalities
| Field | google__gemini-3.1-flash-image-preview | openai__gpt-oss-120b |
|---|---|---|
| Input | image, text | text |
| Output | image, text | text |