Claude Haiku 4.5 vs Mistral Small 3.2
Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-06-29.
Cost at a Glance
Claude Haiku 4.5 is 19.2× more expensive than Mistral Small 3.2 — switching could save 94.8% on your monthly API bill.
At 5M input + 2M output tokens per month:
Choosing Mistral Small 3.2 could save you $14.22/mo
Price Comparison (per 1M tokens)
| Metric | Claude Haiku 4.5 | Mistral Small 3.2 |
|---|---|---|
| Input (per 1M tokens) | $1.00 | $0.07 |
| Output (per 1M tokens) | $5.00 | $0.20 |
| Cache Write (per 1M tokens) | $1.25 | — |
| Cache Read (per 1M tokens) | $0.10 | $0.01 |
| Batch Input (per 1M tokens) | $0.50 | — |
| Batch Output (per 1M tokens) | $2.50 | — |
Prices are per 1 million tokens. Actual costs depend on your monthly token volume. Use the calculator →
Specifications
| Spec | Claude Haiku 4.5 | Mistral Small 3.2 |
|---|---|---|
| Context Window | 1M | 128K |
| Max Output Tokens | 64K | 64K |
| Knowledge Cutoff | 2026-03 | 2025-06 |
| Modalities | Text, Image | Text, Image |
| Prompt Caching | Yes | Yes |
| Batch API | Yes | No |
| Thinking / Reasoning | No | No |
Benchmark Scores
| Benchmark | Claude Haiku 4.5 | Mistral Small 3.2 |
|---|---|---|
| SWE-bench Verified | 55.3 | — |
| MMLU-Pro | 76.8 | 68.0 |
| HumanEval | 88.2 | 85.0 |
Benchmark scores from official provider reports. Higher is better. Missing scores indicate the provider has not published that benchmark yet.
Use Cases
Claude Haiku 4.5
Mistral Small 3.2
About the Providers
Claude Haiku 4.5 is developed by Anthropic. Mistral Small 3.2 is developed by Mistral. This is a cross-provider comparison between Anthropic and Mistral models. For the most up-to-date pricing, always check the official API documentation from each provider.