gemini-3.1-pro-preview is the flagship multimodal model under the Gemini 3.1 architecture. It delivers state-of-the-art reasoning, deep context understanding, and seamless analysis across text, code, images, video, and audio. It is the premier choice for tackling the most complex and demanding enterprise agentic workflows. http://vwdv30vppp.feishu.cn/docx/FC8ZdnCiRo7WKRx6fMvcl0rGnlg
Generate image
All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx
These parameters come from the selected model form_schema. Switching models updates this list and the request example.
system_prompt?stringGlobal instructions or persona for the model.
prompt*stringimage_urls?arraySupports multi-image understanding (optional).
image_detail?stringtemperature?numberHigher values make output more random, lower more deterministic.
top_p?numberNucleus sampling threshold; an alternative to temperature.
presence_penalty?numberIncreases the tendency to talk about new topics.
frequency_penalty?numberReduces the likelihood of repeating the same text verbatim.
max_tokens?numberresponse_format?stringstream?booleancreated?integerParameter description for Created
data?arrayParameter description for Data