Stepfun-Ai/Gelab Zero 4b Preview
by Qiniu · listed Dec 2025TV
StepFun flash model for efficient multimodal reasoning, coding, and tool use
Current rates USD per 1M tokens
Input—
Output—
Cache read—
Cache write—
Against the market
On the record
- Model id
stepfun-ai/gelab-zero-4b-preview- Context window
- 8K tokens
- Max output
- 4K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-12-23
- Last updated
- 2025-12-23
- Provider docs
- developer.qiniu.com/aitokenapi