Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/ne…
Model details →Mistral: Codestral 2508 vs OpenAI: GPT-5 Mini
OpenAI: GPT-5 Mini wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to O…
Model details →Side-by-side comparison
| Capability | Mistral: Codestral 2508 | OpenAI: GPT-5 Mini | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 256K | 400K | 🏆 OpenAI: GPT-5 Mini |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.30 | $0.25 | 🏆 OpenAI: GPT-5 Mini |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.90 | $2.00 | 🏆 Mistral: Codestral 2508 |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | — | Yes | 🏆 OpenAI: GPT-5 Mini |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | Yes | 🏆 OpenAI: GPT-5 Mini |
Frequently asked questions
Is Mistral: Codestral 2508 better than OpenAI: GPT-5 Mini?
OpenAI: GPT-5 Mini wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Mistral: Codestral 2508 and OpenAI: GPT-5 Mini?
Input: $0.30 vs $0.25 per 1M tokens. Output: $0.90 vs $2.00 per 1M tokens.
What context windows do Mistral: Codestral 2508 and OpenAI: GPT-5 Mini support?
Mistral: Codestral 2508 supports up to 256K tokens. OpenAI: GPT-5 Mini supports up to 400K tokens.
Do both Mistral: Codestral 2508 and OpenAI: GPT-5 Mini support tool calling?
Mistral: Codestral 2508: yes. OpenAI: GPT-5 Mini: yes.