gpt-oss-20b is 3.8× cheaper per million tokens (blended). Gemma 4 31B has the larger context window (262,144 vs 131,072 tokens, 2.0×).
Gemma 4 31B vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
Gemma 4 31Bopen
Google · google__gemma-4-31b-it
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | google__gemma-4-31b-it | openai__gpt-oss-20b |
|---|---|---|
| Provider | OpenAI | |
| Slug | google__gemma-4-31b-it | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | google/gemma-4-31B-it | openai/gpt-oss-20b |
Quality
| Field | google__gemma-4-31b-it | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | google__gemma-4-31b-it | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $0.20 | $0.03 |
| Cached input $ / 1M | — | $0.03 |
| Output $ / 1M tokens | $0.40 | $0.13 |
Context
| Field | google__gemma-4-31b-it | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 262,144 | 131,072 |
| Max output tokens | 16,384 | 117,964 |
Modalities
| Field | google__gemma-4-31b-it | openai__gpt-oss-20b |
|---|---|---|
| Input | image, text, video | text |
| Output | text | text |