Mistral Small 3.2 vs Llama 4 Maverick
Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-07-04.
Cost at a Glance
Llama 4 Maverick is 10.3× more expensive than Mistral Small 3.2 — switching could save 90.3% on your monthly API bill.
At 5M input + 2M output tokens per month:
Choosing Mistral Small 3.2 could save you $7.22/mo
Price Comparison (per 1M tokens)
| Metric | Mistral Small 3.2 | Llama 4 Maverick |
|---|---|---|
| Input (per 1M tokens) | $0.07 | $0.80 |
| Output (per 1M tokens) | $0.20 | $2.00 |
| Cache Write (per 1M tokens) | — | — |
| Cache Read (per 1M tokens) | $0.01 | — |
| 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 | Mistral Small 3.2 | Llama 4 Maverick |
|---|---|---|
| Context Window | 128K | 1M |
| Max Output Tokens | 64K | 64K |
| Knowledge Cutoff | 2025-06 | 2026-03 |
| Modalities | Text, Image | Text, Image |
| Prompt Caching | Yes | No |
| Batch API | No | No |
| Thinking / Reasoning | No | No |
Benchmark Scores
| Benchmark | Mistral Small 3.2 | Llama 4 Maverick |
|---|---|---|
| SWE-bench Verified | — | 72.0 |
| MMLU-Pro | 68.0 | 81.0 |
| HumanEval | 85.0 | 89.0 |
Benchmark scores from official provider reports. Higher is better. Missing scores indicate the provider has not published that benchmark yet.
Use Cases
Mistral Small 3.2
Llama 4 Maverick
About the Providers
Mistral Small 3.2 is developed by Mistral. Llama 4 Maverick is developed by Meta. This is a cross-provider comparison between Mistral and Meta models. For the most up-to-date pricing, always check the official API documentation from each provider.