gpt-oss-120b is 3.7× cheaper per million tokens (blended). gpt-oss-120b has the larger context window (131,072 vs 32,768 tokens, 4.0×).
Voxtral Small 24B 2507 vs gpt-oss-120b
Live catalog fields. Best-in-row is highlighted.
Voxtral Small 24B 2507open
Mistral · mistralai__voxtral-small-24b-2507
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Identity
| Field | mistralai__voxtral-small-24b-2507 | openai__gpt-oss-120b |
|---|---|---|
| Provider | Mistral | OpenAI |
| Slug | mistralai__voxtral-small-24b-2507 | openai__gpt-oss-120b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | mistralai/Voxtral-Small-24B-2507 | openai/gpt-oss-120b |
Quality
| Field | mistralai__voxtral-small-24b-2507 | openai__gpt-oss-120b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | mistralai__voxtral-small-24b-2507 | openai__gpt-oss-120b |
|---|---|---|
| Input $ / 1M tokens | $0.10 | $0.02 |
| Cached input $ / 1M | $0.01 | $0.02 |
| Output $ / 1M tokens | $0.30 | $0.09 |
Context
| Field | mistralai__voxtral-small-24b-2507 | openai__gpt-oss-120b |
|---|---|---|
| Max context tokens | 32,768 | 131,072 |
| Max output tokens | 26,214 | 65,536 |
Modalities
| Field | mistralai__voxtral-small-24b-2507 | openai__gpt-oss-120b |
|---|---|---|
| Input | text, audio, file | text |
| Output | text | text |