gpt-oss-120b is 41.7× cheaper per million tokens (blended). Gemini Flash Latest has the larger context window (1,048,576 vs 131,072 tokens, 8.0×). gpt-oss-120b is open-weights; the other is not.
gpt-oss-120b vs Gemini Flash Latest
Live catalog fields. Best-in-row is highlighted.
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Gemini Flash Latest
~google · ~google__gemini-flash-latest
Identity
| Field | openai__gpt-oss-120b | ~google__gemini-flash-latest |
|---|---|---|
| Provider | OpenAI | |
| Slug | openai__gpt-oss-120b | ~google__gemini-flash-latest |
| Status | live | live |
| Open weights | Yes | No |
| License | — | — |
| HuggingFace | openai/gpt-oss-120b | — |
Quality
| Field | openai__gpt-oss-120b | ~google__gemini-flash-latest |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-120b | ~google__gemini-flash-latest |
|---|---|---|
| Input $ / 1M tokens | $0.02 | $0.75 |
| Cached input $ / 1M | $0.02 | $0.07 |
| Output $ / 1M tokens | $0.09 | $3.75 |
Context
| Field | openai__gpt-oss-120b | ~google__gemini-flash-latest |
|---|---|---|
| Max context tokens | 131,072 | 1,048,576 |
| Max output tokens | 65,536 | 65,536 |
Modalities
| Field | openai__gpt-oss-120b | ~google__gemini-flash-latest |
|---|---|---|
| Input | text | text, image, video, file, audio |
| Output | text | text |