DeepSeek V4 Flash vs Mistral Large 3
Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-06-29.
Cost at a Glance
Mistral Large 3 is 20.6× more expensive than DeepSeek V4 Flash — switching could save 95.2% on your monthly API bill.
At 5M input + 2M output tokens per month:
Choosing DeepSeek V4 Flash could save you $24.74/mo
Price Comparison (per 1M tokens)
| Metric | DeepSeek V4 Flash | Mistral Large 3 |
|---|---|---|
| Input (per 1M tokens) | $0.14 | $2.00 |
| Output (per 1M tokens) | $0.28 | $8.00 |
| Cache Write (per 1M tokens) | $0.14 | — |
| Cache Read (per 1M tokens) | $0.00 | — |
| Batch Input (per 1M tokens) | — | — |
| Batch Output (per 1M tokens) | — | — |
Prices are per 1 million tokens. Actual costs depend on your monthly token volume. Use the calculator →
Specifications
| Spec | DeepSeek V4 Flash | Mistral Large 3 |
|---|---|---|
| Context Window | 1M | 256K |
| Max Output Tokens | 64K | 64K |
| Knowledge Cutoff | 2026-05 | 2026-02 |
| Modalities | Text | Text |
| Prompt Caching | No | No |
| Batch API | No | No |
| Thinking / Reasoning | No | No |
Benchmark Scores
| Benchmark | DeepSeek V4 Flash | Mistral Large 3 |
|---|---|---|
| SWE-bench Verified | 79.0 | 68.0 |
| MMLU-Pro | 80.5 | 82.0 |
| HumanEval | 91.2 | 88.0 |
Benchmark scores from official provider reports. Higher is better. Missing scores indicate the provider has not published that benchmark yet.
Use Cases
DeepSeek V4 Flash
Mistral Large 3
About the Providers
DeepSeek V4 Flash is developed by DeepSeek. Mistral Large 3 is developed by Mistral. This is a cross-provider comparison between DeepSeek and Mistral models. For the most up-to-date pricing, always check the official API documentation from each provider.