Gemini 3.0 Flash Preview
by Qiniu · family gemini-flash · listed Dec 2025RTV
New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs
Current rates USD per 1M tokens
Input—
Output—
Cache read—
Cache write—
Against the market
On the record
- Model id
gemini-3.0-flash-preview- Context window
- 1M tokens
- Max output
- 64K tokens
- Input modalities
- text, image, audio, video, pdf
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- Jan 2025
- Released
- 2025-12-17
- Last updated
- 2025-12-17
- Provider docs
- developer.qiniu.com/aitokenapi