Skip to content

Gemini 4 Neon ​

This page lists parameters from the ModelFold model catalog.

Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work. It is suited for repository and terminal coding, web...

Overview ​

FieldValue
Model IDgemini-4-neon
Family sluggemini-4-neon
ModalityChat Models (chat)
EndpointPOST /v1/chat/completions

Request parameters ​

modelstringRequired
Use gemini-4-neon.
messagesarray<object>Required
Conversation messages, at least one.
  messages[].rolestringRequired
Allowedsystemuserassistant
  messages[].contentstringRequired
Message text. Vision models also accept a content array ({"type":"image_url","image_url":{"url":"data:image/png;base64,..."}}).
max_tokensintegerOptional
Maximum tokens to generate.
Default1024
temperaturenumberOptional
Randomness; higher is more varied.
top_pnumberOptional
Nucleus sampling; usually tune this or temperature, not both.

Request example ​

bash
export API_BASE="https://modelfold.ai/v1"
export MODELFOLD_API_KEY="mf-..."   # 在控制台 API Key 页面创建
curl -X POST "$API_BASE/chat/completions" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-4-neon","messages":[{"role":"user","content":"Explain what a diffusion model does in two sentences."}],"max_tokens":512}'

ModelFold — one API for all the best AI models.