The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
Model details →Mistral: Ministral 3 3B 2512 vs Reka Edge
Mistral: Ministral 3 3B 2512 wins on 1 of 6 axes — pricing and capability skew in its favour for most workloads.
Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding, vi…
Model details →Side-by-side comparison
| Capability | Mistral: Ministral 3 3B 2512 | Reka Edge | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 131K | 16K | 🏆 Mistral: Ministral 3 3B 2512 |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.10 | $0.10 | Tie |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.10 | $0.10 | Tie |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| 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: Ministral 3 3B 2512 better than Reka Edge?
Mistral: Ministral 3 3B 2512 wins on 1 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Mistral: Ministral 3 3B 2512 and Reka Edge?
Input: $0.10 vs $0.10 per 1M tokens. Output: $0.10 vs $0.10 per 1M tokens.
What context windows do Mistral: Ministral 3 3B 2512 and Reka Edge support?
Mistral: Ministral 3 3B 2512 supports up to 131K tokens. Reka Edge supports up to 16K tokens.
Do both Mistral: Ministral 3 3B 2512 and Reka Edge support tool calling?
Mistral: Ministral 3 3B 2512: yes. Reka Edge: yes.