Claude Haiku 4.5 vs Qwen 3.7 Max
Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-06-29.
Cost at a Glance
Qwen 3.7 Max is 1.8× more expensive than Claude Haiku 4.5 (45.5% savings if you switch).
At 5M input + 2M output tokens per month:
Choosing Claude Haiku 4.5 could save you $12.50/mo
Price Comparison (per 1M tokens)
| Metric | Claude Haiku 4.5 | Qwen 3.7 Max |
|---|---|---|
| Input (per 1M tokens) | $1.00 | $2.50 |
| Output (per 1M tokens) | $5.00 | $7.50 |
| Cache Write (per 1M tokens) | $1.25 | — |
| Cache Read (per 1M tokens) | $0.10 | — |
| Batch Input (per 1M tokens) | $0.50 | $1.25 |
| Batch Output (per 1M tokens) | $2.50 | $3.75 |
Prices are per 1 million tokens. Actual costs depend on your monthly token volume. Use the calculator →
Specifications
| Spec | Claude Haiku 4.5 | Qwen 3.7 Max |
|---|---|---|
| Context Window | 1M | 1M |
| Max Output Tokens | 64K | 128K |
| Knowledge Cutoff | 2026-03 | 2026-05 |
| Modalities | Text, Image | Text |
| Prompt Caching | Yes | Yes |
| Batch API | Yes | Yes |
| Thinking / Reasoning | No | Yes |
Benchmark Scores
| Benchmark | Claude Haiku 4.5 | Qwen 3.7 Max |
|---|---|---|
| SWE-bench Verified | 55.3 | 80.4 |
| MMLU-Pro | 76.8 | 89.6 |
| HumanEval | 88.2 | 87.2 |
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
Qwen 3.7 Max
About the Providers
Claude Haiku 4.5 is developed by Anthropic. Qwen 3.7 Max is developed by Alibaba. This is a cross-provider comparison between Anthropic and Alibaba models. For the most up-to-date pricing, always check the official API documentation from each provider.