Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...
Model details →Cohere: Command A vs Mistral: Mistral Medium 3.5 (batch)
Mistral: Mistral Medium 3.5 (batch) wins on 6 of 6 axes — pricing and capability skew in its favour for most workloads.
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
Model details →Side-by-side comparison
| Capability | Cohere: Command A | Mistral: Mistral Medium 3.5 (batch) | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 256K | 262K | 🏆 Mistral: Mistral Medium 3.5 (batch) |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $2.50 | $0.75 | 🏆 Mistral: Mistral Medium 3.5 (batch) |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $10.00 | $3.75 | 🏆 Mistral: Mistral Medium 3.5 (batch) |
| Tool / function calling First-class support for emitting structured tool calls. | — | Yes | 🏆 Mistral: Mistral Medium 3.5 (batch) |
| Vision input Accepts image inputs alongside text. | — | Yes | 🏆 Mistral: Mistral Medium 3.5 (batch) |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | Yes | 🏆 Mistral: Mistral Medium 3.5 (batch) |
Frequently asked questions
Is Cohere: Command A better than Mistral: Mistral Medium 3.5 (batch)?
Mistral: Mistral Medium 3.5 (batch) wins on 6 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Cohere: Command A and Mistral: Mistral Medium 3.5 (batch)?
Input: $2.50 vs $0.75 per 1M tokens. Output: $10.00 vs $3.75 per 1M tokens.
What context windows do Cohere: Command A and Mistral: Mistral Medium 3.5 (batch) support?
Cohere: Command A supports up to 256K tokens. Mistral: Mistral Medium 3.5 (batch) supports up to 262K tokens.
Do both Cohere: Command A and Mistral: Mistral Medium 3.5 (batch) support tool calling?
Cohere: Command A: not advertised. Mistral: Mistral Medium 3.5 (batch): yes.