Vispark logo

Vispark

Vision Large

Canonical ID: vispark/vispark/vision-large

Most capable Vision model for complex reasoning, detailed media analysis, and structured output over a 1M-token context window.

Reasoning: Yes Tool use: Yes

Overview

text image audio video pdf
Provider
Vispark logo Vispark
Family
vision-large
Release date
2024-05-15
Last updated
Input modalities
text, image, audio, video, pdf
Output modalities
text

Pricing and Limits

Token pricing

Input
$7.37/1M
Output
$22.11/1M
Cached input
N/A
Currency: USD

Context and output

Context window
1,000,000
Max output tokens
65,536
Qualified ID
vispark/vispark/vision-large

Model Summary

Vision Large is a model listing in the Vispark provider catalog. It is categorized under the vision-large family.

The model supports text, image, audio, video, pdf modalities across input/output paths. Reported context capacity is 1,000,000. Pricing is listed at $7.37/1M input and $22.11/1M output.

More From Vispark

Related models from the same provider catalog.

View all from Vispark