Gemma 4 31B IT vs Ministral 3 3B
Price and specs side by side · USD per 1M tokens · verified 2026-10-11
// side by side
| metric | Gemma 4 31B IT | Ministral 3 3B |
|---|
| input / 1M | $0.14 | $0.10 |
| output / 1M | $0.40 | $0.10 |
| blended (3:1) | $0.205 | $0.10 |
| cache read / 1M | — | $0.01 |
| context | 262.1K | 131.1K |
| max output | 32.8K | 262.1K |
| input types | text · image · video | text · image |
| reasoning | yes | no |
| tool calling | yes | yes |
| structured output | yes | yes |
| open weights | yes | yes |
| released | 2026-04-02 | 2025-12-02 |
| knowledge cutoff | n/a | n/a |
| lab | Google | Mistral |
// monthly cost scenarios
| workload | tokens in / out | Gemma 4 31B IT | Ministral 3 3B |
|---|
| Chatbot | 10M / 2M | $2.20 | $1.20 |
| RAG app | 50M / 5M | $9.00 | $5.50 |
| Coding agent | 20M / 10M | $6.80 | $3.00 |
// verdict
- Ministral 3 3B is 51.2% cheaper than Gemma 4 31B IT on a blended 3:1 input/output basis.
- Gemma 4 31B IT has the larger context window (262.1K vs 131.1K tokens).
- Only Gemma 4 31B IT supports built-in reasoning.