Gemma 4 31B IT vs Voxtral Small
Price and specs side by side · USD per 1M tokens · verified 2026-10-23
// side by side
| metric | Gemma 4 31B IT | Voxtral Small |
|---|
| input / 1M | $0.14 | $0.10 |
| output / 1M | $0.40 | $0.40 |
| blended (3:1) | $0.205 | $0.175 |
| cache read / 1M | — | — |
| context | 262.1K | 32.8K |
| max output | 32.8K | 32K |
| input types | text · image · video | text · audio · pdf |
| reasoning | yes | no |
| tool calling | yes | yes |
| structured output | yes | yes |
| open weights | yes | yes |
| released | 2026-04-02 | 2025-07-15 |
| knowledge cutoff | 2025-01 | n/a |
| lab | Google | Mistral |
// monthly cost scenarios
| workload | tokens in / out | Gemma 4 31B IT | Voxtral Small |
|---|
| Chatbot | 10M / 2M | $2.20 | $1.80 |
| RAG app | 50M / 5M | $9.00 | $7.00 |
| Coding agent | 20M / 10M | $6.80 | $6.00 |
// verdict
- Voxtral Small is 14.6% 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 32.8K tokens).
- Only Gemma 4 31B IT supports built-in reasoning.
- Only Gemma 4 31B IT accepts image input.
- Chatbot (10M input / 2M output tokens per month): Voxtral Small costs $1.80 vs $2.20 for Gemma 4 31B IT, saving $0.40 per month.
- RAG app (50M input / 5M output tokens per month): Voxtral Small costs $7.00 vs $9.00 for Gemma 4 31B IT, saving $2.00 per month.
- Coding agent (20M input / 10M output tokens per month): Voxtral Small costs $6.00 vs $6.80 for Gemma 4 31B IT, saving $0.80 per month.
// Gemma 4 31B IT or Voxtral Small: which one to choose
- Choose Voxtral Small for cost-sensitive, high-volume workloads.
- Choose Gemma 4 31B IT for long documents and large codebases (262.1K-token context).
- Choose Gemma 4 31B IT if you need built-in reasoning.
- Choose Gemma 4 31B IT if you need image input.