qwen3.7-max vs qwen3.7-plus
Side-by-side comparison of qwen3.7-max and qwen3.7-plus: benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API. qwen3.7-max outperforms qwen3.7-plus on 7 of 7 shared benchmarks.
qwen3.7-max
Input / 1M
$2.50
Output / 1M
$7.50
Context
1.0M
Model ID
alibaba/qwen3.7-max
qwen3.7-plus
Input / 1M
$0.40$0.32
Output / 1M
$1.60$1.28
Context
1.0M
Model ID
alibaba/qwen3.7-plus
Benchmark comparison
Intelligence Indexreasoning
qwen3.7-max36.6%
qwen3.7-plus31.9%
Coding Indexcoding
qwen3.7-max66.0%
qwen3.7-plus55.9%
GPQA Diamondreasoning
qwen3.7-max92.3%
qwen3.7-plus90.0%
Terminal-Bench Hardagentic
qwen3.7-max50.8%
qwen3.7-plus47.0%
τ²-Benchagentic
qwen3.7-max94.7%
qwen3.7-plus93.0%
SciCodecoding
qwen3.7-max49.5%
qwen3.7-plus46.1%
Humanity's Last Examreasoning
qwen3.7-max40.5%
qwen3.7-plus35.6%
Scores sourced from official model cards, Artificial Analysis, and public leaderboards. Benchmarks measure specific skills and don't capture every aspect of model quality.
Pricing & specifications
| qwen3.7-max | qwen3.7-plus | |
|---|---|---|
| Input price / 1M | $2.50 | $0.40$0.32 |
| Output price / 1M | $7.50 | $1.60$1.28 |
| Context window | 1.0M tokens | 1.0M tokens |
| Max output | 131K tokens | 131K tokens |
| Vision input | N/A | Yes |
| Tool calling | Yes | Yes |
| Reasoning | Yes | Yes |
| Prompt caching | Yes | Yes |
| Computer use | N/A | N/A |
| Provider | Alibaba Cloud | Alibaba Cloud |
Questions people ask
Is qwen3.7-max better than qwen3.7-plus?
qwen3.7-max outperforms qwen3.7-plus on 7 of 7 shared benchmarks. See the benchmark comparison above for specifics: qwen3.7-max and qwen3.7-plus have different strengths across reasoning, coding, math and multimodal tasks.
Which is cheaper, qwen3.7-max or qwen3.7-plus?
qwen3.7-plus is cheaper. qwen3.7-max costs $2.50/$7.50 per 1M input/output tokens, while qwen3.7-plus costs $0.32/$1.28. The prices shown are what you pay: qwen3.7-plus runs at 20% off its list rate of $0.40 per 1M input and $1.60 per 1M output.
Can I use qwen3.7-max and qwen3.7-plus through the same API?
Yes. Requesty provides a single OpenAI-compatible API that routes to both. Change just the "model" parameter to switch between "alibaba/qwen3.7-max" and "alibaba/qwen3.7-plus", no other code changes needed.
What are the context windows?
qwen3.7-max supports up to 1.0M tokens of context. qwen3.7-plus supports up to 1.0M tokens. Longer context means you can feed larger documents or codebases in a single prompt, though quality often degrades past 128K for most models.
Switch between qwen3.7-max and qwen3.7-plus with one line of code
Requesty provides a single OpenAI-compatible API for 600+ models. Change the model parameter, not your code.