Gemma 3 4B is 6.7× cheaper per million tokens (blended). Mistral Large 3 2512 (batch) has the larger context window (262,144 vs 131,072 tokens, 2.0×). Gemma 3 4B is open-weights; the other is not.
Gemma 3 4B vs Mistral Large 3 2512 (batch)
Live catalog fields. Best-in-row is highlighted.
Gemma 3 4Bopen
Google · google__gemma-3-4b-it
Mistral Large 3 2512 (batch)
Mistral · mistralai__mistral-large-2512--batch
Identity
| Field | google__gemma-3-4b-it | mistralai__mistral-large-2512--batch |
|---|---|---|
| Provider | Mistral | |
| Slug | google__gemma-3-4b-it | mistralai__mistral-large-2512--batch |
| Status | live | live |
| Open weights | Yes | No |
| License | — | — |
| HuggingFace | google/gemma-3-4b-it | — |
Quality
| Field | google__gemma-3-4b-it | mistralai__mistral-large-2512--batch |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | google__gemma-3-4b-it | mistralai__mistral-large-2512--batch |
|---|---|---|
| Input $ / 1M tokens | $0.05 | $0.25 |
| Cached input $ / 1M | — | $0.03 |
| Output $ / 1M tokens | $0.10 | $0.75 |
Context
| Field | google__gemma-3-4b-it | mistralai__mistral-large-2512--batch |
|---|---|---|
| Max context tokens | 131,072 | 262,144 |
| Max output tokens | 16,384 | 209,715 |
Modalities
| Field | google__gemma-3-4b-it | mistralai__mistral-large-2512--batch |
|---|---|---|
| Input | text, image | text, image, file |
| Output | text | text |