gpt-oss-20b is 17.5× cheaper per million tokens (blended). Gemini 3.5 Flash Lite has the larger context window (1,048,576 vs 131,072 tokens, 8.0×). gpt-oss-20b is open-weights; the other is not.
Gemini 3.5 Flash Lite vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
Gemini 3.5 Flash Lite
Google · google__gemini-3.5-flash-lite
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | google__gemini-3.5-flash-lite | openai__gpt-oss-20b |
|---|---|---|
| Provider | OpenAI | |
| Slug | google__gemini-3.5-flash-lite | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | No | Yes |
| License | — | — |
| HuggingFace | — | openai/gpt-oss-20b |
Quality
| Field | google__gemini-3.5-flash-lite | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | google__gemini-3.5-flash-lite | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $0.30 | $0.03 |
| Cached input $ / 1M | $0.03 | $0.03 |
| Output $ / 1M tokens | $2.50 | $0.13 |
Context
| Field | google__gemini-3.5-flash-lite | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 1,048,576 | 131,072 |
| Max output tokens | 65,536 | 117,964 |
Modalities
| Field | google__gemini-3.5-flash-lite | openai__gpt-oss-20b |
|---|---|---|
| Input | text, image, video, file, audio | text |
| Output | text | text |