gpt-oss-20b is 1.9× cheaper per million tokens (blended). Ministral 3 8B 2512 has the larger context window (262,144 vs 131,072 tokens, 2.0×).
Ministral 3 8B 2512 vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
Ministral 3 8B 2512open
Mistral · mistralai__ministral-8b-2512
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | mistralai__ministral-8b-2512 | openai__gpt-oss-20b |
|---|---|---|
| Provider | Mistral | OpenAI |
| Slug | mistralai__ministral-8b-2512 | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | mistralai/Ministral-3-8B-Instruct-2512 | openai/gpt-oss-20b |
Quality
| Field | mistralai__ministral-8b-2512 | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | mistralai__ministral-8b-2512 | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $0.15 | $0.03 |
| Cached input $ / 1M | $0.01 | $0.03 |
| Output $ / 1M tokens | $0.15 | $0.13 |
Context
| Field | mistralai__ministral-8b-2512 | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 262,144 | 131,072 |
| Max output tokens | 209,715 | 117,964 |
Modalities
| Field | mistralai__ministral-8b-2512 | openai__gpt-oss-20b |
|---|---|---|
| Input | text, image | text |
| Output | text | text |