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 (batch) vs Qwen: Qwen3 Coder 30B A3B Instruct
Qwen: Qwen3 Coder 30B A3B Instruct wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
Model details →Side-by-side comparison
| Capability | Mistral: Codestral 2508 (batch) | Qwen: Qwen3 Coder 30B A3B Instruct | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 256K | 262K | 🏆 Qwen: Qwen3 Coder 30B A3B Instruct |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.15 | $0.07 | 🏆 Qwen: Qwen3 Coder 30B A3B Instruct |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.45 | $0.28 | 🏆 Qwen: Qwen3 Coder 30B A3B Instruct |
| 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: Codestral 2508 (batch) better than Qwen: Qwen3 Coder 30B A3B Instruct?
Qwen: Qwen3 Coder 30B A3B Instruct wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Mistral: Codestral 2508 (batch) and Qwen: Qwen3 Coder 30B A3B Instruct?
Input: $0.15 vs $0.07 per 1M tokens. Output: $0.45 vs $0.28 per 1M tokens.
What context windows do Mistral: Codestral 2508 (batch) and Qwen: Qwen3 Coder 30B A3B Instruct support?
Mistral: Codestral 2508 (batch) supports up to 256K tokens. Qwen: Qwen3 Coder 30B A3B Instruct supports up to 262K tokens.
Do both Mistral: Codestral 2508 (batch) and Qwen: Qwen3 Coder 30B A3B Instruct support tool calling?
Mistral: Codestral 2508 (batch): yes. Qwen: Qwen3 Coder 30B A3B Instruct: yes.