Vispark
Vision Small
Fast, low-cost multimodal model for understanding text, images, audio, video, and PDFs, with tool calling and a 1M-token context window.
vispark/vision-small
Context
1M
Output
65.5K
Released
2024-05-15
Knowledge cutoff
—
Types
InputTextImageAudioVideoPDF
OutputText
Reasoning
Supported
Tool use
Supported
Structured output
Supported
Attachments
Supported
Open weights
—
Provider pricing
Vispark
InTextImageAudioVideoPDF
OutText
- Price
- $1.05 / $3.16
- Context
- 1M
- Status
- Stable