Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, inclu…
Model details →Mistral: Mistral Small 3.1 24B vs OpenAI: GPT-4o-mini (2024-07-18)
Mistral: Mistral Small 3.1 24B wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable than other recent frontier mo…
Model details →Side-by-side comparison
| Capability | Mistral: Mistral Small 3.1 24B | OpenAI: GPT-4o-mini (2024-07-18) | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 131K | 128K | 🏆 Mistral: Mistral Small 3.1 24B |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.03 | $0.15 | 🏆 Mistral: Mistral Small 3.1 24B |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.11 | $0.60 | 🏆 Mistral: Mistral Small 3.1 24B |
| Tool / function calling First-class support for emitting structured tool calls. | — | Yes | 🏆 OpenAI: GPT-4o-mini (2024-07-18) |
| Vision input Accepts image inputs alongside text. | Yes | Yes | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Mistral: Mistral Small 3.1 24B better than OpenAI: GPT-4o-mini (2024-07-18)?
Mistral: Mistral Small 3.1 24B wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Mistral: Mistral Small 3.1 24B and OpenAI: GPT-4o-mini (2024-07-18)?
Input: $0.03 vs $0.15 per 1M tokens. Output: $0.11 vs $0.60 per 1M tokens.
What context windows do Mistral: Mistral Small 3.1 24B and OpenAI: GPT-4o-mini (2024-07-18) support?
Mistral: Mistral Small 3.1 24B supports up to 131K tokens. OpenAI: GPT-4o-mini (2024-07-18) supports up to 128K tokens.
Do both Mistral: Mistral Small 3.1 24B and OpenAI: GPT-4o-mini (2024-07-18) support tool calling?
Mistral: Mistral Small 3.1 24B: not advertised. OpenAI: GPT-4o-mini (2024-07-18): yes.