Google
gemini-3-flash-preview API
Call gemini-3-flash-preview by Google through one OpenAI-compatible API. Keep your SDK, change the base URL, and pay per token from your Yeap balance.
New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs
New LLM API accounts get $5 of free credit.
Quick start
Call gemini-3-flash-preview in a few lines
Use any OpenAI SDK or plain HTTP. Point the base URL at Yeap Cloud and set the model name.
curl https://llm.yeap.cloud/v1/chat/completions \
-H "Authorization: Bearer $YEAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3-flash-preview",
"messages": [{"role": "user", "content": "Hello"}]
}'gemini-3-flash-preview variants
Same model with a different reasoning effort, mode or snapshot. Use the exact name in the model field.
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
gemini-3-flash-preview-thinking | $0.5 | $3 |