gpt-oss-120b is 6.6× cheaper per million tokens (blended). Gemini 3.8 Flash has the larger context window (1,048,576 vs 131,072 tokens, 8.0×). gpt-oss-120b is open-weights; the other is not.
Gemini 3.8 Flash vs gpt-oss-120b
Live catalog fields. Best-in-row is highlighted.
Gemini 3.8 Flash
Google · google__gemini-3.8-flash
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Identity
| Field | google__gemini-3.8-flash | openai__gpt-oss-120b |
|---|---|---|
| Provider | OpenAI | |
| Slug | google__gemini-3.8-flash | openai__gpt-oss-120b |
| Status | live | live |
| Open weights | No | Yes |
| License | — | — |
| HuggingFace | — | openai/gpt-oss-120b |
Quality
| Field | google__gemini-3.8-flash | openai__gpt-oss-120b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | google__gemini-3.8-flash | openai__gpt-oss-120b |
|---|---|---|
| Input $ / 1M tokens | $0.82 | $0.15 |
| Cached input $ / 1M | $0.08 | $0.07 |
| Output $ / 1M tokens | $4.13 | $0.60 |
Context
| Field | google__gemini-3.8-flash | openai__gpt-oss-120b |
|---|---|---|
| Max context tokens | 1,048,576 | 131,072 |
| Max output tokens | 65,536 | 65,536 |
Modalities
| Field | google__gemini-3.8-flash | openai__gpt-oss-120b |
|---|---|---|
| Input | text, image, video, file, audio | text |
| Output | text | text |