Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local …
Model details →Mistral: Mistral Small 3 vs Qwen2.5 72B Instruct
Mistral: Mistral Small 3 wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized…
Model details →Side-by-side comparison
| Capability | Mistral: Mistral Small 3 | Qwen2.5 72B Instruct | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 33K | 33K | Tie |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.05 | $0.12 | 🏆 Mistral: Mistral Small 3 |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.08 | $0.39 | 🏆 Mistral: Mistral Small 3 |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Mistral: Mistral Small 3 better than Qwen2.5 72B Instruct?
Mistral: Mistral Small 3 wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Mistral: Mistral Small 3 and Qwen2.5 72B Instruct?
Input: $0.05 vs $0.12 per 1M tokens. Output: $0.08 vs $0.39 per 1M tokens.
What context windows do Mistral: Mistral Small 3 and Qwen2.5 72B Instruct support?
Mistral: Mistral Small 3 supports up to 33K tokens. Qwen2.5 72B Instruct supports up to 33K tokens.
Do both Mistral: Mistral Small 3 and Qwen2.5 72B Instruct support tool calling?
Mistral: Mistral Small 3: yes. Qwen2.5 72B Instruct: yes.