Vispark models
Vispark has 3 models in the directory. The newest is Vision Large, released May 15, 2024.
The cheapest to run is Vision Small at $1.05 per million input tokens.
Vision Large has the longest context window, 1M tokens.
- Models
- 3
- Newest
- May 15, 2024
- From
- $1.05/M input
- Longest context
- 1M
All Vispark models
Filter in the directory- 1M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning.
by visparkMay 15, 2024$7.37/M input tokens$22.11/M output tokens
- 1M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning.
by visparkMay 15, 2024$4.21/M input tokens$12.63/M output tokens
- 1M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning.
by visparkMay 15, 2024$1.05/M input tokens$3.16/M output tokens
Prices and context from models.dev (MIT licensed), refreshed Oct 24, 2026.