qwen/qwen3-7-plus
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.
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
frequency_penalty | number | Frequency penalty. Positive values penalize tokens proportionally to how often they have appeared, reducing repetition. | 0 | min: -2, max: 2 |
image | array | Optional list of input images for visual understanding (Qwen3.7-Plus is multimodal). Each image is sent alongside the text prompt. | | — |
max_tokens | integer | The maximum number of tokens the model should generate as output. | 2048 | min: 1, max: 65536 |
presence_penalty | number | Presence penalty. Positive values penalize tokens that have already appeared, encouraging the model to talk about new topics. | 0 | min: -2, max: 2 |
prompt | string | The prompt to send to the model. | "" | — |
system_prompt | string | System prompt to guide the model's behavior. | "You are a helpful assistant." | — |
temperature | number | The value used to modulate the next token probabilities. | 0.7 | min: 0, max: 2 |
top_p | number | A probability threshold for nucleus sampling. Only keeps the top tokens with cumulative probability >= top_p. | 0.8 | min: 0, max: 1 |
frequency_penaltynumberFrequency penalty. Positive values penalize tokens proportionally to how often they have appeared, reducing repetition.
0min: -2, max: 2imagearrayOptional list of input images for visual understanding (Qwen3.7-Plus is multimodal). Each image is sent alongside the text prompt.
max_tokensintegerThe maximum number of tokens the model should generate as output.
2048min: 1, max: 65536presence_penaltynumberPresence penalty. Positive values penalize tokens that have already appeared, encouraging the model to talk about new topics.
0min: -2, max: 2promptstringThe prompt to send to the model.
""system_promptstringSystem prompt to guide the model's behavior.
"You are a helpful assistant."temperaturenumberThe value used to modulate the next token probabilities.
0.7min: 0, max: 2top_pnumberA probability threshold for nucleus sampling. Only keeps the top tokens with cumulative probability >= top_p.
0.8min: 0, max: 1b964682d1c19Updated: 7/25/202614 runs
cinemasetfree.com