gpt-oss-20b is 75.0× cheaper per million tokens (blended). Gemini 4 Argon 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 4 Argon vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
Gemini 4 Argon
Google · google__gemini-4-argon
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | google__gemini-4-argon | openai__gpt-oss-20b |
|---|---|---|
| Provider | OpenAI | |
| Slug | google__gemini-4-argon | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | No | Yes |
| License | — | — |
| HuggingFace | — | openai/gpt-oss-20b |
Quality
| Field | google__gemini-4-argon | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | google__gemini-4-argon | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $2.00 | $0.03 |
| Cached input $ / 1M | $0.10 | $0.03 |
| Output $ / 1M tokens | $10.00 | $0.13 |
Context
| Field | google__gemini-4-argon | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 1,048,576 | 131,072 |
| Max output tokens | 943,718 | 117,964 |
Modalities
| Field | google__gemini-4-argon | openai__gpt-oss-20b |
|---|---|---|
| Input | audio, file, image, text, video | text |
| Output | text | text |