gpt-oss-20b is 1.7× cheaper per million tokens (blended). gpt-oss-20b has the larger context window (131,072 vs 128,000 tokens).
Mistral Small 3.2 24B vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
Mistral Small 3.2 24Bopen
Mistral · mistralai__mistral-small-3.2-24b-instruct
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | mistralai__mistral-small-3.2-24b-instruct | openai__gpt-oss-20b |
|---|---|---|
| Provider | Mistral | OpenAI |
| Slug | mistralai__mistral-small-3.2-24b-instruct | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | mistralai/Mistral-Small-3.2-24B-Instruct-2506 | openai/gpt-oss-20b |
Quality
| Field | mistralai__mistral-small-3.2-24b-instruct | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | mistralai__mistral-small-3.2-24b-instruct | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $0.07 | $0.03 |
| Cached input $ / 1M | — | $0.03 |
| Output $ / 1M tokens | $0.20 | $0.13 |
Context
| Field | mistralai__mistral-small-3.2-24b-instruct | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 128,000 | 131,072 |
| Max output tokens | 16,384 | 117,964 |
Modalities
| Field | mistralai__mistral-small-3.2-24b-instruct | openai__gpt-oss-20b |
|---|---|---|
| Input | image, text | text |
| Output | text | text |