qwen/qwen3-7-plus 🖼️🔢📝 → 📝
Performance
2.4sTypical run time
378.4KTotal runs
About
Qwen3.7-Plus is Alibaba's cost-effective multimodal model with vision-language understanding, a 1 million token context window, and strong agentic coding and tool use.
Example Output
Prompt:
"Explain why the sky is blue to a curious 10-year-old, in 3 short sentences."
Output
Sunlight looks white, but it is actually made of all the colors of the rainbow mixed together. When this light hits the air, the blue part scatters in every direction much more than the other colors. This scattered blue light fills the sky, which is why we see it as blue when we look up!
Performance Metrics
2.43s
Prediction Time
2.45s
Total Time
All Input Parameters
{
"prompt": "Explain why the sky is blue to a curious 10-year-old, in 3 short sentences.",
"max_tokens": 200
}
Input Parameters
- image
- Optional list of input images for visual understanding (Qwen3.7-Plus is multimodal). Each image is sent alongside the text prompt.
- top_p
- A probability threshold for nucleus sampling. Only keeps the top tokens with cumulative probability >= top_p.
- prompt
- The prompt to send to the model.
- max_tokens
- The maximum number of tokens the model should generate as output.
- temperature
- The value used to modulate the next token probabilities.
- system_prompt
- System prompt to guide the model's behavior.
- presence_penalty
- Presence penalty. Positive values penalize tokens that have already appeared, encouraging the model to talk about new topics.
- frequency_penalty
- Frequency penalty. Positive values penalize tokens proportionally to how often they have appeared, reducing repetition.
Output Schema
Output
Version Details
- Version ID
b964682d1c195be9959b5ebab520cb203fafd1d3b318b4893ebbb68ac8acfd98- Version Created
- June 25, 2026