GPT-4o mini is cheaper than Mistral Devstral Medium at $0.15/M vs $0.4/M input tokens.
| Spec | Mistral Devstral Medium | GPT-4o mini |
|---|---|---|
| Input price | $0.4/M tokens | $0.15/M tokens |
| Output price | $2/M tokens | $0.6/M tokens |
| Context window | — | 128K tokens |
| Released | Jul 2025 | Jul 2024 |
Not enough votes to call it. On the specs, Mistral Devstral Medium has the edge: bigger model tier, newer.
GPT-4o mini costs 3.3x less per token.
GPT-4o mini is cheaper on both — 2.7× input, 3.3× output
GPT-4o mini uses 5.4x more headings
GPT-4o mini is cheaper than Mistral Devstral Medium at $0.15/M vs $0.4/M input tokens.
| Spec | Mistral Devstral Medium | GPT-4o mini |
|---|---|---|
| Input price | $0.4/M tokens | $0.15/M tokens |
| Output price | $2/M tokens | $0.6/M tokens |
| Context window | — | 128K tokens |
| Released | Jul 2025 | Jul 2024 |
Not enough votes to call it. On the specs, Mistral Devstral Medium has the edge: bigger model tier, newer.
GPT-4o mini costs 3.3x less per token.
GPT-4o mini is cheaper on both — 2.7× input, 3.3× output
GPT-4o mini uses 5.4x more headings