GPT OSS Safeguard 120B vs Voxtral Small 24B 2507
Price and specs side by side · USD per 1M tokens · verified 2026-10-11
// side by side
| metric | GPT OSS Safeguard 120B | Voxtral Small 24B 2507 |
|---|
| input / 1M | $0.15 | $0.10 |
| output / 1M | $0.60 | $0.30 |
| blended (3:1) | $0.2625 | $0.15 |
| cache read / 1M | — | — |
| context | 128K | 32.8K |
| max output | 16.4K | 8.2K |
| input types | text | text · audio |
| reasoning | yes | no |
| tool calling | yes | yes |
| structured output | yes | yes |
| open weights | yes | yes |
| released | 2025-10-29 | 2025-07-15 |
| knowledge cutoff | n/a | n/a |
| lab | OpenAI | Mistral |
// monthly cost scenarios
| workload | tokens in / out | GPT OSS Safeguard 120B | Voxtral Small 24B 2507 |
|---|
| Chatbot | 10M / 2M | $2.70 | $1.60 |
| RAG app | 50M / 5M | $10.50 | $6.50 |
| Coding agent | 20M / 10M | $9.00 | $5.00 |
// verdict
- Voxtral Small 24B 2507 is 42.9% cheaper than GPT OSS Safeguard 120B on a blended 3:1 input/output basis.
- GPT OSS Safeguard 120B has the larger context window (128K vs 32.8K tokens).
- Only GPT OSS Safeguard 120B supports built-in reasoning.